model

Browse files

Files changed (14) hide show

.gitattributes +1 -0
README.md +40 -0
config.json +1 -0
humanoid-v5-TQC-simple.zip +3 -0
humanoid-v5-TQC-simple/_stable_baselines3_version +1 -0
humanoid-v5-TQC-simple/actor.optimizer.pth +3 -0
humanoid-v5-TQC-simple/critic.optimizer.pth +3 -0
humanoid-v5-TQC-simple/data +126 -0
humanoid-v5-TQC-simple/ent_coef_optimizer.pth +3 -0
humanoid-v5-TQC-simple/policy.pth +3 -0
humanoid-v5-TQC-simple/pytorch_variables.pth +3 -0
humanoid-v5-TQC-simple/system_info.txt +8 -0
replay.mp4 +3 -0
results.json +1 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,40 @@

+---
+library_name: stable-baselines3
+tags:
+- Humanoid-v5
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TQC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Humanoid-v5
+      type: Humanoid-v5
+    metrics:
+    - type: mean_reward
+      value: 5543.17 +/- 825.31
+      name: mean_reward
+      verified: false
+---
+# **TQC** Agent playing **Humanoid-v5**
+This is a trained model of a **TQC** agent playing **Humanoid-v5**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+## Usage (with Stable-baselines3)
+TODO: Add your code
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
+...
+```

config.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVKgAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMCVRRQ1BvbGljeZSTlC4=", "__module__": "sb3_contrib.tqc.policies", "__annotations__": "{'actor': <class 'sb3_contrib.tqc.policies.Actor'>, 'critic': <class 'sb3_contrib.tqc.policies.Critic'>, 'critic_target': <class 'sb3_contrib.tqc.policies.Critic'>}", "__doc__": "\n Policy class (with both actor and critic) for TQC.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the feature extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n :param n_quantiles: Number of quantiles for the critic.\n :param n_critics: Number of critic networks to create.\n :param share_features_extractor: Whether to share or not the features extractor\n between the actor and the critic (this saves computation time)\n ", "__init__": "<function TQCPolicy.__init__ at 0x7f5dae87bf60>", "_build": "<function TQCPolicy._build at 0x7f5dae8a4040>", "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7f5dae8a40e0>", "reset_noise": "<function TQCPolicy.reset_noise at 0x7f5dae8a4180>", "make_actor": "<function TQCPolicy.make_actor at 0x7f5dae8a4220>", "make_critic": "<function TQCPolicy.make_critic at 0x7f5dae8a42c0>", "forward": "<function TQCPolicy.forward at 0x7f5dae8a4360>", "_predict": "<function TQCPolicy._predict at 0x7f5dae8a4400>", "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7f5dae8a44a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f5dae886340>"}, "verbose": 0, "policy_kwargs": {"use_sde": false}, "num_timesteps": 1965000, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": 0, "action_noise": null, "start_time": 1739115667059208301, "learning_rate": 0.0003, "tensorboard_log": "runs/0", "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVeAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYFAAAAAAAAAAEBAQEBlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksFhZSMAUOUdJRSlC4="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV1jYAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZgNgAAAAAAAI+mDODskfQ/7iCWcSdY7j+9wbK1ywmiP45PPuzZybS/fX4ZSYaD07+1b6SitsrdP1c+dqmaTLo/fgTL5hYyp7+5zAMXMIfXv5AL1BNxL/G/M5SXWlEH2T9lMd6xkYyWP0UVy8mXybs/vh4gWyli5D+iAg6n2AGkPzfUGR+lS4C/DTaHtREF+L8SWNTy0UX3v2CwC9a3Mvm/9BhJ+1cKvL8MZr3GJsThPxZ3Wy2IIOw/YcwVGJ7Y6j/dotB6vzDQv5dE8qhTLa+/De37vtno8D/9KGRM1/rkP3tOgxP88/W/hp+qr1mG+z+QWEzZC2qcP7B5p5iZrALAsvmc6cpW4j+fu7K456PzPxRH/rQ+mei/EvQEU6PeBMDoQmXsecbWv2WdguM2faW/UO9dqmX36D/+rucq9WTBvxAa1kD9Ltg/UhVtQkYD8b9r+sND7rycP4xq8OCwSvI/8RQco6StA0DHwU5GiFS+v2GgtrVRcgJA+ne1EXFuAkBLrgaEiF6nP33LWRbU+YO/RUKsZjxDsz+wdXIR2riAPzUsvYBOcr2/YyKRfVXUh7+Ed9wq4ngRQAscZ+ie0CFAZ6qfSUhbuT+qE3hUODi4P7QiIdRMv4c/VXxgM0wEWL9SvIOXCUCIv9FPz55/93G/7V4bBINvrj96t/BGCUyVP+nNOCs5vdw//QtahHcYAkCs1COz25SuP/WgIlYLkqE/bqmGEzmMrD/RuAlZfkF4v5gD3cWgenC/E3OZS14+Zr+ny1CJQMm/P8TXl/eP7rU/lKtos4iDyz+65PaX+3YaQGTBUrQ/gNA/KX4QtZZXzD9hQSBNigSoP5rHfT/BNXU/E2pzmqzEcz+omx8oIOCyvySEy8L5tq0/+RgVuAoI278hEvO4v6Hqv3zX1/7KARNAyYj5O0Aa7T9QaZuA6WXsP/oLSmiTgp0/D2w70ADTeL8HP/dftNyjv5jdK6gHV8K/UTEaJKZ6sL/ViZVn/WPQvxjbw4Qlifi/XiGebqoLBkCq8VFZGnjwP8sJJdAnQPA/qXFDPlb2mD+S/6bP7wh/v85jSzS12a2/CuOuHvLFwL9hdvQsOsKzv4e/tlWHNMa/YSp8N5Jb9b+7ssy+Okb8P55rRIE6gtA/iRXRGvk3zj8IIh0xihSwP81caooIPZm/BDMMJ6lOqT8rghBqX/OwP+dIeFhZ19E/M2HEti732j8iyLlS7p7qv3zX1/7KARNA29aPJaqJ7D8z5Bv+ibDsP4sPLgAY5ZY/nZw3dcWRgr8SygmObAK6Px4qKt2eF7M/+m9xNn83xz/CL3uSD8LBP3KgU30Hhfi/XiGebqoLBkCUAhwKETnwP+Q9lZOVVfA/ko5+pc4tjj/VVRVOAc1wv1518GXoMbg/2adg/Exmpj/xVnZkawTAP6wOHrpPqK0/n5TI4t5a9b+7ssy+Okb8Px4wjlSboNU/wk7/vMtM2j++MPYk1sXAPztDedjoX6m/oxdsQNBxxD+kbGMbAOm3P2RQPfsVyti/dYtH84a+y7/kFniD+sTmP352ZiHJk/o/tE4rtrlNwT+Tjdtol3jgP8gewRICots/GD+SMkIdur/NH4muYvnJP6bawzOWpKo/XEDPIEdB5r+KYALNka7Gv1fW+1isUNc/fTtVVjKs8z+th9MWu+jZP12thc+tMNg/EMm0aeaOvj+L/GnoAVKtv+5zPhRzPby/1stmRPSAwr+bFlg9OcHQP+uO/vkepdU/G/Z2caF95z9+dmYhyZP6P/aimJgz/NI/ITA2kyvv0z9TyZSABPW2P8GNEaIyg6W/TUlIsqGHvL91XEupgxC1v4N02VLICtA/S2z8pW3xyD8jCZ4JaNjhP307VVYyrPM/4iNXyFVl9z+yHGkPUdavv24Y/K6fKPK/v5gOWhjW6z/0z857xDDaP/MNbNcRWa2/tyeTDPyL8j+Qg1tvaAquv2uNK7A16uE/O/hhayky7D/YkCOLncjSP01VSTo+Mqy/V1RnQfs48r+NavbfNnLTP8RdLSWkbdg/qdYHsZSU6j9A1d/7hv6Av+Y6TgjEXZK/XAbIDmIj9b/UVBX7TuTbPw6may8EVvo/uiRvmZz75j+pU3ycqXekv9gJ7zi6kp+/apRvry5s8j/o7ArE+n/zP/sC6/4i9/U/enAOije78D9Mb7UMQvzvv+AzFAvEcsc/apRvry5s8j/o7ArE+n/zP/sC6/4i9/U/enAOije78D9Mb7UMQvzvv+AzFAvEcsc/YKpjghWtzb/iktKWyXbpPzdip7e4rNo/ZovDiEjM6j+cx7WLDDqQv4Qk4b5xfra/jAHDdO8swb/1fCwqE3/sPzkvlSnjS9o/9EAkm2j16z8FVXiQ4kSrv4D8kR/Qoba/jAHDdO8swb/1fCwqE3/sPzkvlSnjS9o/9EAkm2j16z8FVXiQ4kSrv4D8kR/Qoba/2Xn3N8t0AEBgEpKIy2/tv9fehanJ/Pi/tRbAdAOw9T8FvrVRr/7kP1VJKCDgj78/RWorpU1lAECagX4+jsLsvybGy5G+t/i/pfxOXCKK9T9eySIQYB7lP8atTMPbQb0/cn7SG8dNBkCsXP5tNc3aP4Zn2nHt7/I/E9ktVKmX7T/cpIiE7rntP4l/6LVWJ8m/7kythTKpBkCerpr9wibfPxu4CDHJUPQ/2CqIkByv7T+N5Tv+4X7tP6bXMJCYnci/AAAA8n8QNEAAAABgfT7xPwAAANA3XR3AAAAA6n3cP0AAAAAioNUywAAAgL1OOF1AAAAAYGwgA0AAAAA1IiRBQAAAAH3QGEJAAAAAgJn7N0AAAAAbYMJSQAAAAN3y/yHAAAAAlfIHIcAAAADHg50iwAAAAGjl+/W/AAAAwClq3z8AAAAK1wccQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAHGLNKwmcxHAgq6jRd5nQ0BxizSsJnMRwDtw0/gdOEbAAAAAAAAAAAA7cNP4HThGQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACGiLMJ/P1JApLTTJyY9KMBqPfVGLQEXQMhOC74e90nAWD3wROCWTEBR5emcq1yIQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAALYRM9PklfM/DNqN69uO7D8CfFBr2sfIPzbMQpdUV6y/0X0VKOzW2b9bJboTnnDpPy5NnSKnt8G/DzGRDkhv5L947ETPHCTRv7vZyoedVOG/3eyiG7u91z8ITIXXJwGEv/Z0nB+Riqw/QtnNgKKs1D/VjvmExivaP9+JDhPKG9+/rm6Rjmwg7r9oTMh+fOrwv33A0Lv73/W/x4B1GBHL8L+1acI00D3Lv4IKMnqGOfm/YrhWeV3Y8D9pN1Jj63/Fv/63/9PXouA/HutxZjoXCEDQz7fsqIQLwJcd31DSeQrAHopQ+jHI4D8Z/XDuTnsdQCaVuteKdeo/GnvhB8rZ4j8EvCkis38jwLfqIt4Yw9S/YTFIgumsKECyuTqkSmX+vxjfndT9yvm/uUOT5jog3r+5lE+iWMESQFbN9PknRAPAywOJMMcQG0BApgAccgUSQEU3aE8q4bA/qW0OyxkW1D+A9iqUj75qP4CUWsAoygBA9eV3U6EBAUCHQVk02zS3P7hZ4P11Lo6/mQuc2D470T9w3Vki1e1/P2nqjaC91+C/MmMndFEZrT+VSlD83KIQQAscZ+ie0CFAQITY52VDvz8B1fyGZ1W4P7gBTwMOqqA/bbSfNaRacr8mDnTW1xuCv+K9g+kV6Ke/tcPKhp+mpj/kmwDMkNPMP5QlA2gZ2tw//QtahHcYAkBjz3J7eT69P9oPhPdANrA/uuzqBxIKvz9ndeRIb+2jv6laJ10ygI+/ePP0Chyvk7+IWRO+ywvYP2yfLECeV+I/JuZ2Awdu0z+65PaX+3YaQMY76LvgeMU/r5X+zO1vwz80rtaTwHiwP2srIttP9pg/tAkIVrS5oj+or80AtEKwvwQucHFTx9M/7hRkPV6817/BOGZuvaDhv3zX1/7KARNAMuwlO37W6D9jpyFLFmLlP21Wx8ORD8E/UGGECYQ4oj9anQCgyTG1P/cee7ls2NG/fEoltyVYxj/kEKmnjRLivw7WS2apC/W/XiGebqoLBkDxMfOhxF7tP7cubKDkZOk/coKChuEDwj8omLPMZEOdP0T5SedS7LE/MeFnt5d21L84Itr7jeu6Pzlz8zo+vN6/e9PI4iLT8r+7ssy+Okb8P3JS+nkZ99I/RfTALfwO0T/PncoGv3vBP4SrR1nEsK+/5se+sDOhtD/4JDikyEy3P5UcR5/k5N4/QcU86wo44z9RzNbPn6Dqv3zX1/7KARNAJqdK44/z6j9uxxSlxVrqP7q6TqY6hqE/6UBmxzBaab+a52o+y0OIP4HGxB/PI8I/F6RKz+FApj/E3q8ru67QP2mjM/dSnfe/XiGebqoLBkBPeS8oGL7tPwLK4KufVe0/EAJLGHegoT8bR04j4VCMP3uFg+845ba/0FcQRc3iwT8rbHJQsgHAv9ddtgtDAsk/JR4qX6w49L+7ssy+Okb8P7wjoaMQo80/4CwZ2/YL2D86F0LT/V3HP2mqVzVfMau/bslVzYDuxT++TsMf08avPxi9MU/7EeC/RimPfUR2xr/Sv5pgL8/iP352ZiHJk/o/4V6SQ/Wauj8yHV0+U7LfP52X83q3EOA/31mYvDHpw79oEN4G9MTBP0J8eFOotqc/7cuPP6mA578LOEgooRzQv7Yaii4hkM4/fTtVVjKs8z8kzohqLeTUP9oljnY3VNU/5Yrq46LalD/9Cy1OL555vxLMRjmm2K2/5fkfjFszpb93mobqQT/CP+LMaDhk9bU/Mu0osTvY5j9+dmYhyZP6P459qyloSqs/4OE/vEbPsD/lbjslx7uvP42sfk/fKJ0/3Jo2N+u8mb+En9yArwKNP0Oj/Hok9Mo/U5yH+P7Hw79VNfEdJJLEP307VVYyrPM/9Ok6n36/2j++FndyZ1AKwFsU1bPppxHAUk7B69hIA0Ba9iWuWizJv16yQJouZuU/xpk0UYsW2D/UBeE5xtELQKAkui41bvq/ZlKe7gjR7D9XqNh+vITIv/A+vm5hReQ/bs7Gdxj08T+FLaPKlPMKQL6TTPpJpPW/xs7Nz5pw7j+z/0pvh065v741ga45TeE/Ag1dQ6WODEDFtRcBu7QEwE5jhm18sCHAl0ZhFd449j+zk6zXruzeP46dUMSGRMw/Z1s/XFebFMDDO97mVa0jwLrbMIf3YhjAMyDbXk4U9b9PVK6W4IYIQPK1gMX33fi/Z1s/XFebFMDDO97mVa0jwLrbMIf3YhjAMyDbXk4U9b9PVK6W4IYIQPK1gMX33fi/6a0/wbCSAUBIJDqFsRELQJJMUM6oY+0/IuhbfjUp9T/w31ApOD7Xv6bA/TQHeNc/CC8iZRwn0r9Aj3bvCObYv3RzbDuYcvw/4CHEnUjbqr9iwzHEQ1DgP+UbzNxIhc0/CC8iZRwn0r9Aj3bvCObYv3RzbDuYcvw/4CHEnUjbqr9iwzHEQ1DgP+UbzNxIhc0/6P/n3lewEsCFvYtKYfH1vwBikW+Awqc/KecWQGQS8j9UBSCQo574vwh3m2v+q8u/6XHhCzu5G8DoxABIV+nrv5rM8TeKRw9AMi7kaIi64j+Qf0zMMUTZv+jbmbYw1OW/alpVDbbM5T8KB93ylWYKwJzDR7d+cBHAjr3wsiJgA0CQL6UcADarv9Fgt/REjOQ/bGlBRCO/5T8+Jp9lO2cKwDbUzMHJcBHAgBHYtlBgA0BmCxF4TWyrv+tBJWDZi+Q/AAAAxRWuQkAAAAAAlTQYwAAAAB8IrEPAAAAAzwSSMsAAAAAvbvlDwAAAgC83lFtAAAAACwuaU0AAAABcIlMqwAAAACbJhTdAAACAoObqXEAAAABF1j9TQAAAAOey/CPAAAAAEk41EEAAAADIM7cAQAAAAIpebxbAAAAA1mPpI8AAAADJRgYiwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAOxQw/UBskxAYGQcjggfV0CisZMkbTkfQB/XwqZc0lnASEf3kGyISUBiPZ93SUtjQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAB9cD+FjWfQ/2ddXfY0n7j8fURQTUGW8P2ifpIm6gp4/1DFz1ZQe1D+uIfam1tOyv2HA8/1IAMW//4CYAXlv079vuR2JHjjOv9bCJdzMIOm/XX7vG7gM2D9aE7IkXWCGP8XjgOZQZKQ/arzRdasYvD/jwMLWTVmrPxbHZ/ydZHs/qQTAnhfWzr8qqy0/rIjLP3nTUJhMOfm/Isb6dxtO67/Gt+Tlb0rsvxS5FiNUU/W/ASgfWpeW5T/po8hOQ+arP56XHHThjZu/1Fh73p4C1L8jg0PS62kBwIyEQpYiQOo/gHzpeaUdfL82bif34l0FQLybAQeSnMU/cmGAi1zj2T9sezqxILLxv6qYMyQkbaS/0vXe3YQZ9j+Ux/l4W3LQP7lZVWSTwwZA6I6ZnpHm8j/I9Gck0niVv6oMsTUSagvALp7Ojq7/vL+ITLWPTlZvv57zhQW/OQ7AwWLv8g9N9L9w6v5gxrQiwJt552qT4wFAzZDMBvzKAUCQmz+bXkGzPzB6oPGSI1u/nFCELIdUwT+KErh4ol/KP47aVN+dN9S/DbnHDMvq2L8PJ3wqcB0RQAscZ+ie0CFAFvsl2gwKuD+KgAVRjxy6P5UmQtfMXZU/ok2tb7Nwcz/uDy77RgGgP2zoA7xH6Xy/xqq62UAexL+pI/nmXS+fP8H8DGnZHdw//QtahHcYAkAGdj5aTTasP1d6bkvearE/CA+ahmArtj+6ghJQcTCXP0gj3wPYyok/L61OYMu0aL95P7tnKdzcv1LRQTBV+cM/Iy+CpjdzyT+65PaX+3YaQL1rEarXG80/KuovOBvlyj+Vb3c73tSaP4fpFqDrUFm/gBpyLMONf7+ysukA4ZaqvzAmqEGcvZa/ttpJTk1w0r8E7MDGwabpv3zX1/7KARNA0LvJN9Zj7D97DNZn4MvrP6CrF3ajupo/s/VDqjZce7+C79sgqDWmv4jAiA7LDsG/PCJP6W1ms78Are3SRHPOv3OBb5cMQvi/XiGebqoLBkCtaHxsHTvwPzy5yMPk8+8/bfRZMgPfmT987R978fd8vwo93Sppcaq/Lox+Faliwb+XjYSo26Wxv3qQDh+uNMe/M8WKYsMu9b+7ssy+Okb8P6yax69nVdI/fjglOlAL0D+hVHUjE+22P6Fz6wG8SKI/vvN2Jfrqp79OT+TEO0+3P1HMWRgdQ9S/urFMs+7X4D9FuveM7XPrv3zX1/7KARNAjzv6qNlO7T91ezho7I7sP3bMoymr95w/bKskk45aYD992D53SQh7v1Fbeyd/XMI/4vz3wxNGlL8tx9gxGorQPxvFVTuRoPi/XiGebqoLBkCVGXe4rnHwP1RaELkkPvA/guA3JMj0kj/pt2t1Ic9tvyQjGNbIFKA/PSuGbzH2vT9rj7iV20SlP1j3Tx9M0MM/fvzxoLpg9b+7ssy+Okb8PxfTf87PWdU/969WcI7D1j+8DtLNTJnAP6jsM8oHqa0/V3VoeJI1wL8NrG1iTwu/P8/bkP+mvNQ/PAWAcXsE078g2exVkLDlP352ZiHJk/o/ponMu2LlwD9+0g0khhTeP9ErwYHQf9g/3x5MIUBEtT9nX0gN95nIv+apFr0K+Kg/QytG51Xx5D/FEB3DGLbEv0tHEEjCZ9c/fTtVVjKs8z9DJuLSyQjcP1I0WJP2Nts/OgqssB6Poz9h77A9yIBkv+o/C4N7OIA/7r90hb0Mub+BjypaAFh8vwVINX8Chsk/iihcikhq6j9+dmYhyZP6P4EdyU5I59Q/+tEaGqTZ2z/qTDwXKgzJP/CgxJL8PrS/XcUOCa++yb/V1IIQHk68v+ySqvHDgto/R/WxkbRzzT/JTuMJ8djiP307VVYyrPM/P08BEsOY8T+kIqOdjDIAwK/qBDPLeNM/r0BCsuoM+T9Urj4C8cHhP8LhrOaMZrU/lBGYkwzj0b+AwnFm4jvAP3y7a1kA0Os/VoOR7X8s8D9Gy/2bVtLOP2AQukXbF7O/TALZ5Ec4sb89i+oxpxjQP8PusIZAHu0/Z8UaN+7c7z8gjHyRK2HRP3/GukGp/ba/s8WOR8xo4T+L7WyUEV7BP8cDt+okx8u/HT4RFnPf8D9RXnuJT87RP8ByMMgG/q2/8ObcgePvwT/fCUqOlBHzv/AG2TMKzbW/dw0jCBFB4T9yAA0BEs7bP74hsH3xeLC/8ObcgePvwT/fCUqOlBHzv/AG2TMKzbW/dw0jCBFB4T9yAA0BEs7bP74hsH3xeLC/rsGqWSJ20L9GAs9A1n7yP6uc7uxUHgDAjk0EfEPo5D9ALyWw4f4gP7rcqKOvZMO/IOC6XVn40L++n5At5cryP9eR0yYNIgDAoh0W1jYi5T/V64JUVQBqPzyOHK0jX8O/IOC6XVn40L++n5At5cryP9eR0yYNIgDAoh0W1jYi5T/V64JUVQBqPzyOHK0jX8O/Chw/5fMB4b/swFQZv94RwLvBs/uHvfe/kONcW88zCECmPxNXgPC0v17+y7xRNNi/+fixCEkM4b98DczjA9wRwILmOkKcyPe/9exXtfcyCECo78J7xs20v5repLadKNi/eW3+8sLNAcCVR2T6xgwNwIVJ7f4NL/O/VmVtIU59AkChAa5U8Cz3v92Y3f6uauI/+vyiouPyDsC2Hj2OkEoVQDtQMQE51vA/KpcVmurv87/3dNE32BoEwKw7HEJztQFAAAAASr2kMsAAAABLnq5CQAAAANQa0yVAAAAAr9X6QUAAAADkPohDwAAAgLvC1ltAAAAA1YYUUkAAAAD1sxQ1wAAAAORiwy1AAACAwfCXV0AAAACXiglRQAAAADGE5iPAAAAAD6GSIkAAAACxYO4jwAAAANTw7h7AAAAA7wP5I8AAAABKMTcWwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAPEZz26ioWbATfDlg3neb0A69w8J+CY3wDDOumTu/HHAZfQ+lxBtZMBiSFqwdjN8QAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAALpEcVy7CmpACMmX3kR3SMBw8xJxJp7nP/iTzPDX8z5A0Hq2voZXYkB0fkzeE/mOQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAI1GFkiZYfQ/xh0oh5Sf7z8wqEuwlGSwP/WH6ylc/2q/RpFFSh3HwT8eQM2w/MnHv9nX4sAqT8a/9/qV5jpOsr+pk9MS5JjZvw0qGokbBOm/y6EZI89t1z9DrnprEorXv41BNCzDtKM/7BjPPdD01j9MWL+6fKG0vwFUs0ET6ty/achVl5Xd97+Cm8D8AzXpv7RaD7DBOPm/HwJtod8P7L+UcnxoZtHhv2SUmxDse+o/8PV8JUBJ6z/QqTnNHzK8vynqMyzSD7+/NLgcaHZw/j/hsy+HZkIGQMxDB+CaGPC/FIqgCXW497++Y9wGBdMVwL/EkawKbQTAbBhUpq52+z+TVZtYhmUPQBSR9kxLtbK/oHNAGQ9Krj/ihSTImwe7P+gdpAHKqBRALDPQC2lKE0BINwBi/wsVQFgdyde2zPQ/mJpOynIhCMCDtoyLhhqbP2D1NbtRwtw/mq9dMLSEDMAAyhRMvy3WP3pIWuRROwFAt1ppDZQYAUC6ygYADTupP7uDEFNSJWQ/NfRFVnt+tD9eRwzRS3y2P5wOJtTf3Ma/36bdyHIyxL/Rsg3c7csQQAscZ+ie0CFAB7yiK5V6tT+a9J+FKfuzP4Fb9yL5Uoc/UuOYFXaMVj9zpdzXzkGAP7Wsgi5YNIG/xhDhPHtepr8XtAlhMq+lP4BBdpS0D9o//QtahHcYAkBU+z2qRU2vPzbsTvWFfJs/OJWaK+gFrz90aljTVkdzP4pnC6JrzVM/hGhzqBEydL/JgZubQbayv9pD9Szqocw/IXRJaHvzuD+65PaX+3YaQHeTVbclD9I/asLx416U0D8CrGByKlOhP/YP4jOmFXQ/GOoK5OnmhT+Bk+yIGgOyvzTTP4MqT7I/rFx8PCit1b8KK88FVtztv3zX1/7KARNAbFfDEzaG7T+NXh6QjJHtP9QuceokeJc/6FgDytlCeb/0bQfP7wq3v4S4+651rrS/tn+2RQBSwr8+3xwp41PDvy+feNUd/Pi/XiGebqoLBkCc90tCuRXwPzCOKIkhdvA/1jKHYeqYnT/g4BvlINBwv7iWvzeD7sO/YLWukZMCm78xH9cy1XzKvzzDZ+918qG/AIMkAbNG9b+7ssy+Okb8P9GZVQyd49M/fA3uk9bBzj8OBvQ+MyO8P37mfV81A6C/Nvl1fM68rT9Wv/Lo6ii9P09X52kTBc4/AM0MEKJ25D/t47d+zlrrv3zX1/7KARNAB6jt/W8C7j/EYvkJTFzsP7z67PqAzrU/z4o/o4jPnr+q4hbmcsa6P2D+Ju8Hr84/S2BEgEhsyT9KAod4IFfbP5xSWwViV/i/XiGebqoLBkC50Uw86sfwP3LVDJGgw+8/SsImZsefsD8H2/nnMT6IvwFvUo/d3qg/6mMcY5HDzj9rsnPlPKWwP7yC8cz8ltQ/ebozWnIf9b+7ssy+Okb8P1EvjoNZIuI/xPd4j+sD2T/v/zBiYhDHP1+ZV2sLP4W/a98qExkbhD+HDJXxWDPQPw7feAeQQ5S/rmlb9fG04L8snHBwiLDpP352ZiHJk/o/VG+lKNl37T+FUp9LkFPYP+DjmP40yOE/FOX5FwT6r79ZTPzhbmSqP/vlrkTEyNw/VdJ+pmrmt79EnilzyPrpvysLAO9NnuU/fTtVVjKs8z8+jQ/Mb5XWPxsBDx3bltU/yOONIQRhpj9XRqcA6uGDv9+3YfAHw5y/jf3SXqOvuL//b0sSfHq0PwRP4y9JDMw/EGLfeZM+5z9+dmYhyZP6P2ypFHSDN9U/5OiqdHMA1T8q99BEuzqfPxw6sGN/LYq/1PFsUFTIqL9JQDv7QiuyvyMKeiyd4rs/LBKiyGpLwj92ft1/TJfjP307VVYyrPM/ceNPn0HU8D+L+t4xN3MKQGmOu42CQuO/zlWrXpu64r/lZ089f63VPyxuXn8adcW/K9HtvIDA+D9GUZtyq2v+vwAvHmz9PgbAmFxh1a0u5T8dbDGRlDPZPzBwbzCjKJC/crUVhl2f7r/hvK/jzJsAwKeosKNe7QnAOcLt0BRs5T+wdpyZrg65P7a9ESiMlaw/Tk9Fq/YBtL8YmZjBhcnnv4PsCPV3lOc/kkyd8jJ93T8AgU2a/xeUvxFnXzkZFsI/8k7a3aDtvr+kbJpqxjbpv5Cr8OZLyuc/Fz6YQ4lJ3D8wcUA1yRtiv3/6fM/tmsE/8k7a3aDtvr+kbJpqxjbpv5Cr8OZLyuc/Fz6YQ4lJ3D8wcUA1yRtiv3/6fM/tmsE/BmRrfTMK8z/IHjcLJ8cFQOY+9tlnuB/AtLJUjby+uD9sEPJ8nNy5P9zuSoyhAsq/GMfV/dne0L/exxpmj5wCwBDBp8DjuyDACeWk2j2V/r+Io77nFqHmP5RfgH+G2eC/GMfV/dne0L/exxpmj5wCwBDBp8DjuyDACeWk2j2V/r+Io77nFqHmP5RfgH+G2eC/cAJ3hbUMEEByLcYvPBUKQLhczkh9NwDAMtewzihv079u70HsQZr8PzxjvbvEudc/W9VvERv0D0CMtQ9SJyMKQH+eHBTNEgDAgFVJJscy1L/wQcD+Gnr8Pz4WK9WcI9c/ogSor3oQ6j944yQlYErRv+Betllz5+y/BCvgvmeX8z8ofgoxeSbJP56peSOLW7g/Y647veQP6D/UvONfC3bjv7dLsYZmXe6/btMfuNpS9T/uGdaOe47HP6oOU7J+76M/AAAALU0qQEAAAAAXOS5DwAAAAKuQ+0PAAAAALbNYMsAAAABXB/1CwAAAACq2fTrAAAAAwQXzU0AAAABvD382wAAAAC38+UNAAACAbFn2XUAAAABBtfVTQAAAALbKHBxAAAAAalQbF8AAAAB7uOUjwAAAAB7t5SPAAAAA8J3HI8AAAACEDyMHQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEmpyz4He/Q/fCsuRJEc7j+Khr20mKGzPxXUp6ZMyZ8/eIECatIA1T9WJukVl+zNv/qAC1o2rsm/07CzT66nyb+vC5uzS7jQv53wMVKUFey/kL15/CxX1z9bJZDJ3MmWv5OHq11jULS/hpzaF5Ze0r9wB6ZLpPiiv15IblvBSMC/qaDEk0Ysyb9zXOYSy0TDP7sXJgezO/m/VfndviY06r9299+l8qjwvxguKQEHibA/htXcrL0x5T8Sle9PtNuOv6LXxHQ/27M/EzdBYVA76r/IcRY0UwOxP+w0mqsj7AnALTvNcqvU8D+ePeiRvyvrvxcXuPr9hwJAjDO70YC5+b+ChIvcYgHZv6qKU80ZPNc/uR44UNk9tr+Egf5zBcGSP8OlAN6jwPa/Rf/6Lnaq4T+xS47GWIEIwETIWgD/x+a/f6VstxGgCkDaxbWrA7d+P0UEy9RENPs/DJX3H67R9j9ie0NuhSkBQGk5xEUVugFAH5/iikOoAUAbL1Cl/w2yP+jlwUzVEF+/dquUCAPWwD/gdnFdlVXIP9m2RxQ4mtO/53VLuObm17+Cq934OAkRQAscZ+ie0CFAlH7wV8XMtj94Q0bFV+q3P6EAiitWcJI/NoZV1lupWj8vssUXrcSaP6Gx5wllgVI/Z2vhTp5+wb+SfbojncKFv475s0uzQts//QtahHcYAkA5EXwS3HGqP7TmP2rtx6s/flHmbVoRsz/2GtSMTneHPyvfMuJLM4E/zLRZR8xXOz+z2AfHX3vYv7tk7ooV15g/C8zY7sWCwz+65PaX+3YaQDddHj9mm9A//PQeIrknzT/sPA+4oJmkPz2FJ6EiS0i/VeUUQB52cr+Sx6bIoRuyv8vJgB8idYG/bFszLkjl2L8Svbux30Trv3zX1/7KARNAxjgYo72S7T/uK0ZaEOfsPz2MRYUqsZw/MGCh0PU7er8krMkQwiylv4Owh9Y2J8K/9ZINf+fOsb+76sqC4BDQv/BWhasAwvi/XiGebqoLBkCwGPrBIbLwP1ffAVYmevA/PojfNbwfmD9glaJ/nrh8v8A5XgssKay/a5xt7h2xwL9lelgGz4Gyv9rU58SD8MW/GlqiPfCC9b+7ssy+Okb8PzShecxrbNM/5LxoxFUVzz/0YaLQ3Au3P5sm0+ah15c/VnsxA5T0mb+g6tWEW+a8P2HIYTout8m/PCNDYsOG4j8RbMSJtejrv3zX1/7KARNALQ0HubLk7j9guzzf3d3sP2frIGnaHrE/Kx+vj8p1Yb+aKISn9j6DP1xFOxY7Os4/ke7dVQW4iz+aGCUFSMPaP6HvpOUsxPi/XiGebqoLBkCyKk312CvxPy/EHfTWc/A/gFEiFaORqT/A0f/WwOdzv9WGvW+unpc/+/yjgeWbyz/iPJHhLAifP2JBYH3tItI/Hx5taVqF9b+7ssy+Okb8PxAUPXuBjdU/ZJ3Vc0EM1z8DknB+6ZrAPxjpciW+8K0/rBBEWBNrwL99BwakJf++P/stZ/T58dQ/7xLUyt3n0r+fD3NfRdDlP352ZiHJk/o/slYabXf8vj9sFFnrzd3cPw0E5ERiMNg/sFs38SzxtT+/mqC+38TGvxBeADlJbKg/rHZHAEPC5D9h4S2Ton7Fv3oPnSko+NU/fTtVVjKs8z8dis8GqADdP2s5pNLgKtw/+8frUsbXpD+cN8iVIUtpv4dh25uQJXI/MwitG2tdur8PwJopAuJuvwMiV+KAOso/vTh6DlXk6j9+dmYhyZP6P5MFZOnh7eE/7cXiVUkC4j/rKME8lOykP8GgdTVdgpS/pWtZ//t0ur8NZFFVkUS4v3ygt9GrksQ/aszAcE4Ywz/pSrpABM7pP307VVYyrPM/XfDdPFOR8L/QcCTTxGisv9g+tl+qbQnA02P1Asik6T9VRDLLZt/iv3+RPyGSkqU/bEkYbHo94r8HAyKsqYXuv/+aNx+fNALALFr4Tuos8D8IXTpZ7Hfavy9yE94BAbw/oriEbXl4+D8Qoa6/cEOovyqw6Yi5g/6/p9NhtuXU7D+0af6sV7/Av1abfFU8vaQ/FEHslIAt1j/srlSaMA7cvxdBUyD8WQTAzyHWebVU7j9xnAAdy6+9v7ha11p2f6y/kwhmXFvf2D8AEU5jai7Xv733CDphZQTAaMQ//UNN7z9QDo0cEvfAv5jkatp0G6u/kwhmXFvf2D8AEU5jai7Xv733CDphZQTAaMQ//UNN7z9QDo0cEvfAv5jkatp0G6u/drj25psb7z89JXcc/mbNP+fT+0EseeC/mQkipkDS8D9aT2zpnjCVv7mqeJClKbQ/yva3x7fM77/ibVgC3JsEQOYQnUcZF+G/vlIM0xCA/z/aBZMleAHoPy/mNYIVY9Y/yva3x7fM77/ibVgC3JsEQOYQnUcZF+G/vlIM0xCA/z/aBZMleAHoPy/mNYIVY9Y/yD9HCR6txL+7ltE0BVgFwECsGW/a0fK/578Hg0IU+z87vun9Q7nUvwAkUwyvZSw/8Q4a2vlVxL8Yg1w7gmEFwGgzbqpfvPK/l103yZwW+z/GM/YF/sjUv0ysDVfOO06/wiiRUv0Mzz/HQd8AaLj4PxzZlvgRmwLAwKnf5kzqmj+dOHko1QDKP4NrQJuKM9K/GaAyj+W15j9SZPrqVQ7gv9btVb9hJAbAp5eu8v+K7T9oTxwM/8XfP1+5CgLBOua/AAAAPM2nLEAAAADStQM/QAAAAJ52pzFAAAAAWQGNQ8AAAADmaf4/wAAAgJer8lxAAAAAHdhDUkAAAAA4jKgwwAAAAMCbwBrAAACAtyMeXUAAAACujz1RwAAAAFOetyDAAAAAolitG0AAAADnSbYjwAAAACqwrxZAAAAAvOkkB8AAAAD6iMMdQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEYGd/F1ml7AvBXQ5FHHc0BBRFWFILo+wFKPVD8KSHbAsTtqfmqJV8A+Hu/eZCp8QAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEbkqgWWUUxAD3KU09VKX8DvkWOePdg2wPUhRoq6QGJAMGCqiUarQEABurAsjGtmQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLBU1cAYaUjAFDlHSUUpQu"}, "_episode_num": 6167, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.017502499999999976, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 392979, "buffer_size": 1000000, "batch_size": 256, "learning_starts": 100, "tau": 0.005, "gamma": 0.99, "gradient_steps": 1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}", "__doc__": "\n Replay buffer used in off-policy algorithms like SAC/TD3.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n of the replay buffer which reduces by almost a factor two the memory used,\n at a cost of more complexity.\n See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n Cannot be used in combination with handle_timeout_termination.\n :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n separately and treat the task as infinite horizon task.\n https://github.com/DLR-RM/stable-baselines3/issues/284\n ", "__init__": "<function ReplayBuffer.__init__ at 0x7f5dab3b4d60>", "add": "<function ReplayBuffer.add at 0x7f5dab3b4ea0>", "sample": "<function ReplayBuffer.sample at 0x7f5dab3b4f40>", "_get_samples": "<function ReplayBuffer._get_samples at 0x7f5dab3b4fe0>", "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7f5dab3b5080>)>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f5dab5e0240>"}, "replay_buffer_kwargs": {}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "target_entropy": -17.0, "ent_coef": "auto", "target_update_interval": 1, "top_quantiles_to_drop_per_net": 2, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float64", "_shape": [348], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]", "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False]", "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf]", "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False]", "low_repr": "-inf", "high_repr": "inf", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [17], "low": "[-0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4\n -0.4 -0.4 -0.4]", "bounded_below": "[ True True True True True True True True True True True True\n True True True True True]", "high": "[0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4]", "bounded_above": "[ True True True True True True True True True True True True\n True True True True True]", "low_repr": "-0.4", "high_repr": "0.4", "_np_random": "Generator(PCG64)"}, "n_envs": 5, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "batch_norm_stats": [], "batch_norm_stats_target": [], "system_info": {"OS": "Linux-6.1.125-1-MANJARO-x86_64-with-glibc2.41 # 1 SMP PREEMPT_DYNAMIC Fri Jan 17 15:04:03 UTC 2025", "Python": "3.12.8", "Stable-Baselines3": "2.4.1", "PyTorch": "2.5.1+cu124", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "Gymnasium": "1.0.0"}}

humanoid-v5-TQC-simple.zip ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4814a61d04158a9535cec8d8173d4e2cb4f7be2e070b257b9d27215539d65735
+size 7375841

humanoid-v5-TQC-simple/_stable_baselines3_version ADDED Viewed

	@@ -0,0 +1 @@


1	+ 2.4.1

humanoid-v5-TQC-simple/actor.optimizer.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e74201e498739b1b483912062391270ffbdb5adbbe26eb94e8af8cb44c925041
+size 1317710

humanoid-v5-TQC-simple/critic.optimizer.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:787b9e206b18a13b0c2b08203fa084d95c966dd6a5771225d65ba19a1b4ed242
+size 2664106

humanoid-v5-TQC-simple/data ADDED Viewed

	@@ -0,0 +1,126 @@

+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVKgAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMCVRRQ1BvbGljeZSTlC4=",
+        "__module__": "sb3_contrib.tqc.policies",
+        "__annotations__": "{'actor': <class 'sb3_contrib.tqc.policies.Actor'>, 'critic': <class 'sb3_contrib.tqc.policies.Critic'>, 'critic_target': <class 'sb3_contrib.tqc.policies.Critic'>}",
+        "__doc__": "\n    Policy class (with both actor and critic) for TQC.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the feature extractor.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    :param n_quantiles: Number of quantiles for the critic.\n    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ",
+        "__init__": "<function TQCPolicy.__init__ at 0x7f5dae87bf60>",
+        "_build": "<function TQCPolicy._build at 0x7f5dae8a4040>",
+        "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7f5dae8a40e0>",
+        "reset_noise": "<function TQCPolicy.reset_noise at 0x7f5dae8a4180>",
+        "make_actor": "<function TQCPolicy.make_actor at 0x7f5dae8a4220>",
+        "make_critic": "<function TQCPolicy.make_critic at 0x7f5dae8a42c0>",
+        "forward": "<function TQCPolicy.forward at 0x7f5dae8a4360>",
+        "_predict": "<function TQCPolicy._predict at 0x7f5dae8a4400>",
+        "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7f5dae8a44a0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f5dae886340>"
+    },
+    "verbose": 0,
+    "policy_kwargs": {
+        "use_sde": false
+    },
+    "num_timesteps": 1965000,
+    "_total_timesteps": 2000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1739115667059208301,
+    "learning_rate": 0.0003,
+    "tensorboard_log": "runs/0",
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVeAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYFAAAAAAAAAAEBAQEBlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksFhZSMAUOUdJRSlC4="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_episode_num": 6167,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.017502499999999976,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 392979,
+    "buffer_size": 1000000,
+    "batch_size": 256,
+    "learning_starts": 100,
+    "tau": 0.005,
+    "gamma": 0.99,
+    "gradient_steps": 1,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
+        "__module__": "stable_baselines3.common.buffers",
+        "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}",
+        "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n        Cannot be used in combination with handle_timeout_termination.\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7f5dab3b4d60>",
+        "add": "<function ReplayBuffer.add at 0x7f5dab3b4ea0>",
+        "sample": "<function ReplayBuffer.sample at 0x7f5dab3b4f40>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f5dab3b4fe0>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7f5dab3b5080>)>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f5dab5e0240>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -17.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "top_quantiles_to_drop_per_net": 2,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float64",
+        "_shape": [
+            348
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]",
+        "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False]",
+        "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf]",
+        "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False]",
+        "low_repr": "-inf",
+        "high_repr": "inf",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            17
+        ],
+        "low": "[-0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4 -0.4\n -0.4 -0.4 -0.4]",
+        "bounded_below": "[ True  True  True  True  True  True  True  True  True  True  True  True\n  True  True  True  True  True]",
+        "high": "[0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4 0.4]",
+        "bounded_above": "[ True  True  True  True  True  True  True  True  True  True  True  True\n  True  True  True  True  True]",
+        "low_repr": "-0.4",
+        "high_repr": "0.4",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 5,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": []
+}

humanoid-v5-TQC-simple/ent_coef_optimizer.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5816e3744618243063dbd8632b3889201b51d2441801e6c83b6a6e779f0b016f
+size 1940

humanoid-v5-TQC-simple/policy.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ca9aff0dc359d6011ddde33f196fc8b612781cba80247fb8a9889eb1df74e58e
+size 3321014

humanoid-v5-TQC-simple/pytorch_variables.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:16f7205a840137b520ff4c800236c4e440d3168e362d68055dac78565ccd476c
+size 1180

humanoid-v5-TQC-simple/system_info.txt ADDED Viewed

	@@ -0,0 +1,8 @@

+- OS: Linux-6.1.125-1-MANJARO-x86_64-with-glibc2.41 # 1 SMP PREEMPT_DYNAMIC Fri Jan 17 15:04:03 UTC 2025
+- Python: 3.12.8
+- Stable-Baselines3: 2.4.1
+- PyTorch: 2.5.1+cu124
+- GPU Enabled: False
+- Numpy: 1.26.4
+- Cloudpickle: 3.1.0
+- Gymnasium: 1.0.0

replay.mp4 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:495ce13d206c150ef17df9f012fc97222de432034394df6d5e886850ddde3bdd
+size 1283689

results.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"mean_reward": 5543.171139794, "std_reward": 825.3107032616788, "is_deterministic": true, "n_eval_episodes": 1000, "eval_datetime": "2025-02-10T22:01:38.033217"}