Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -19.03 +/- 3.50
+      value: -0.21 +/- 0.09
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d453b85c81529f7ce20d6de4de0657ef4d23eaff1da289bc1dcc6999e26ad366
-size 106951
+oid sha256:dd478cb81a23b0a64565d3f5a8db063bbd3274793749b4821503a604f197f895
+size 111043

a2c-PandaReachDense-v3/data

@@ -4,9 +4,9 @@
         ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=",
         "__module__": "stable_baselines3.common.policies",
         "__doc__": "\n    MultiInputActorClass policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space (Tuple)\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 ortho_init: Whether to use or not orthogonal initialization\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 full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` 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 squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Uses the CombinedExtractor\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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    ",
-        "__init__": "<function MultiInputActorCriticPolicy.__init__ at 0x7da62c709360>",
+        "__init__": "<function MultiInputActorCriticPolicy.__init__ at 0x7bd88b5b65f0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7da62c864d80>"
+        "_abc_impl": "<_abc._abc_data object at 0x7bd88b5d1e80>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -19,30 +19,30 @@
             "weight_decay": 0
         }
     },
-    "num_timesteps": 100,
-    "_total_timesteps": 100,
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1737253668348623137,
+    "start_time": 1737254273738624121,
     "learning_rate": 0.0007,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'collections.OrderedDict'>",
-        ":serialized:": "gAWVuwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QoljAAAAAAAAAADaKhP+KmIb75BJG/D85Nv8DyH8Drcny/sbUhv9mkvj/6rJe/oCFTP/+4HL/qN56/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksESwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcoljAAAAAAAAAAlCAkv2nAbD8PS0o+GUMbv5VqT7+Fe8c/AfXPP5BVnT8C4Wi/pzlEvwQIjr/09ri+lGgOSwRLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWYAAAAAAAAAANoqE/4qYhvvkEkb+Wox2/GEc2v9JvBMAPzk2/wPIfwOtyfL+v2mG+OCZSPkhPO7+xtSG/2aS+P/qsl7/ncIA/PKWfPg4Mvz+gIVM//7gcv+o3nr9Oy/s+AFEwPx4NuD+UaA5LBEsGhpRoEnSUUpR1Lg==",
-        "achieved_goal": "[[ 1.2627579  -0.15786317 -1.1329643 ]\n [-0.80392545 -2.4991913  -0.9861285 ]\n [-0.63167864  1.4894058  -1.1849663 ]\n [ 0.8247318  -0.6121978  -1.2360814 ]]",
-        "desired_goal": "[[-0.6411221   0.92481095  0.19755195]\n [-0.6064926  -0.81022006  1.558457  ]\n [ 1.6246644   1.2291737  -0.90968335]\n [-0.7665047  -1.1096196  -0.3612591 ]]",
-        "observation": "[[ 1.2627579  -0.15786317 -1.1329643  -0.6157774  -0.7120223  -2.069325  ]\n [-0.80392545 -2.4991913  -0.9861285  -0.22056077  0.20522392 -0.7316785 ]\n [-0.63167864  1.4894058  -1.1849663   1.0034455   0.3118075   1.4925554 ]\n [ 0.8247318  -0.6121978  -1.2360814   0.49178547  0.68873596  1.4379003 ]]"
+        ":serialized:": "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",
+        "achieved_goal": "[[-1.0788736e-01 -5.1694256e-01 -2.3632760e-01]\n [ 3.0607727e-01 -5.0742464e-04  4.5547619e-01]\n [ 1.4392481e+00 -1.0880989e+00 -1.0174804e+00]\n [ 3.0607727e-01 -5.0742464e-04  4.5547619e-01]]",
+        "desired_goal": "[[-0.47684428 -1.4825408  -0.7608834 ]\n [-0.5081798   0.857459   -1.4667604 ]\n [ 1.5451307  -0.73299223 -1.4573857 ]\n [-0.65606064  0.6111825  -1.0399253 ]]",
+        "observation": "[[-1.0788736e-01 -5.1694256e-01 -2.3632760e-01 -1.7536658e+00\n  -1.6624295e+00 -1.3761318e+00]\n [ 3.0607727e-01 -5.0742464e-04  4.5547619e-01  4.7416279e-01\n  -3.5803586e-03  3.9202911e-01]\n [ 1.4392481e+00 -1.0880989e+00 -1.0174804e+00  3.2231233e-01\n  -1.9069903e-01 -1.6300983e+00]\n [ 3.0607727e-01 -5.0742464e-04  4.5547619e-01  4.7416279e-01\n  -3.5803586e-03  3.9202911e-01]]"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAABAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
     },
     "_last_original_obs": {
         ":type:": "<class 'collections.OrderedDict'>",
-        ":serialized:": "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",
+        ":serialized:": "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",
         "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]]",
-        "desired_goal": "[[ 0.03731203  0.06901985  0.05952062]\n [-0.07100393  0.00964756  0.23240362]\n [ 0.12530066  0.13395402  0.08713633]\n [-0.08508232 -0.00860164  0.11941493]]",
+        "desired_goal": "[[-0.04923796  0.00346506  0.19945097]\n [-0.1287942   0.09131246  0.18100132]\n [-0.03500744  0.01078671  0.2686623 ]\n [ 0.00462093 -0.01123007  0.01163375]]",
         "observation": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]]"
     },
     "_episode_num": 0,
@@ -52,13 +52,13 @@
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWVRQAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUfZQojAFylEe/7Whh6Skj5owBbJRLCIwBdJRHQBiiwW3z+WJ1YS4="
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 5,
+    "_n_updates": 50000,
     "n_steps": 5,
     "gamma": 0.99,
     "gae_lambda": 1.0,

a2c-PandaReachDense-v3/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c095c66dffb41948cfb7b307fc3c43ecb6c7982f8569d60169d82531b59d49c5
+oid sha256:72166c0217d670d15d3795e9da38c33305c3bfd4a120b989e270b741e0c56e40
 size 48200

a2c-PandaReachDense-v3/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:470b8ed80d37723f1ee777a1dea575a24a086c0868ff4fcdbead9ff006f22f96
+oid sha256:f7ac62b11ab4dd468bad79618dd4808bc62ab08dd6f1079a11a1cf9083fe89eb
 size 46319

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    MultiInputActorClass policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space (Tuple)\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 ortho_init: Whether to use or not orthogonal initialization\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 full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` 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 squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Uses the CombinedExtractor\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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    ", "__init__": "<function MultiInputActorCriticPolicy.__init__ at 0x7da62c709360>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7da62c864d80>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 100, "_total_timesteps": 100, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1737253668348623137, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 1.2627579  -0.15786317 -1.1329643 ]\n [-0.80392545 -2.4991913  -0.9861285 ]\n [-0.63167864  1.4894058  -1.1849663 ]\n [ 0.8247318  -0.6121978  -1.2360814 ]]", "desired_goal": "[[-0.6411221   0.92481095  0.19755195]\n [-0.6064926  -0.81022006  1.558457  ]\n [ 1.6246644   1.2291737  -0.90968335]\n [-0.7665047  -1.1096196  -0.3612591 ]]", "observation": "[[ 1.2627579  -0.15786317 -1.1329643  -0.6157774  -0.7120223  -2.069325  ]\n [-0.80392545 -2.4991913  -0.9861285  -0.22056077  0.20522392 -0.7316785 ]\n [-0.63167864  1.4894058  -1.1849663   1.0034455   0.3118075   1.4925554 ]\n [ 0.8247318  -0.6121978  -1.2360814   0.49178547  0.68873596  1.4379003 ]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]]", "desired_goal": "[[ 0.03731203  0.06901985  0.05952062]\n [-0.07100393  0.00964756  0.23240362]\n [ 0.12530066  0.13395402  0.08713633]\n [-0.08508232 -0.00860164  0.11941493]]", "observation": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]]"}, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVRQAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUfZQojAFylEe/7Whh6Skj5owBbJRLCIwBdJRHQBiiwW3z+WJ1YS4="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 5, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "normalize_advantage": false, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True]", "bounded_above": "[ True  True  True]", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.6.56+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Nov 10 10:07:59 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.1.0", "PyTorch": "2.5.1+cu121", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "Gymnasium": "0.29.0", "OpenAI Gym": "0.25.2"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    MultiInputActorClass policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space (Tuple)\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 ortho_init: Whether to use or not orthogonal initialization\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 full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` 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 squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Uses the CombinedExtractor\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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    ", "__init__": "<function MultiInputActorCriticPolicy.__init__ at 0x7bd88b5b65f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7bd88b5d1e80>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 1000000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1737254273738624121, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[-1.0788736e-01 -5.1694256e-01 -2.3632760e-01]\n [ 3.0607727e-01 -5.0742464e-04  4.5547619e-01]\n [ 1.4392481e+00 -1.0880989e+00 -1.0174804e+00]\n [ 3.0607727e-01 -5.0742464e-04  4.5547619e-01]]", "desired_goal": "[[-0.47684428 -1.4825408  -0.7608834 ]\n [-0.5081798   0.857459   -1.4667604 ]\n [ 1.5451307  -0.73299223 -1.4573857 ]\n [-0.65606064  0.6111825  -1.0399253 ]]", "observation": "[[-1.0788736e-01 -5.1694256e-01 -2.3632760e-01 -1.7536658e+00\n  -1.6624295e+00 -1.3761318e+00]\n [ 3.0607727e-01 -5.0742464e-04  4.5547619e-01  4.7416279e-01\n  -3.5803586e-03  3.9202911e-01]\n [ 1.4392481e+00 -1.0880989e+00 -1.0174804e+00  3.2231233e-01\n  -1.9069903e-01 -1.6300983e+00]\n [ 3.0607727e-01 -5.0742464e-04  4.5547619e-01  4.7416279e-01\n  -3.5803586e-03  3.9202911e-01]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAABAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "gAWVuwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QoljAAAAAAAAAA6nIdPRlsGqxDI0o+6nIdPRlsGqxDI0o+6nIdPRlsGqxDI0o+6nIdPRlsGqxDI0o+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksESwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcoljAAAAAAAAAAvq1JvfoVYzvgPEw+oOIDvgcCuz1pWDk+9WMPvb66MDwbjok+NmuXO1T+N7x7mz48lGgOSwRLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWYAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAACUaA5LBEsGhpRoEnSUUpR1Lg==", "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]]", "desired_goal": "[[-0.04923796  0.00346506  0.19945097]\n [-0.1287942   0.09131246  0.18100132]\n [-0.03500744  0.01078671  0.2686623 ]\n [ 0.00462093 -0.01123007  0.01163375]]", "observation": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]]"}, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_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": 50000, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "normalize_advantage": false, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "gAWVsAMAAAAAAACMFWd5bW5hc2l1bS5zcGFjZXMuZGljdJSMBERpY3SUk5QpgZR9lCiMBnNwYWNlc5SMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwUZ3ltbmFzaXVtLnNwYWNlcy5ib3iUjANCb3iUk5QpgZR9lCiMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowNYm91bmRlZF9iZWxvd5SMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYDAAAAAAAAAAEBAZRoE4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksDhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoHCiWAwAAAAAAAAABAQGUaCBLA4WUaCR0lFKUjAZfc2hhcGWUSwOFlIwDbG93lGgcKJYMAAAAAAAAAAAAIMEAACDBAAAgwZRoFksDhZRoJHSUUpSMBGhpZ2iUaBwolgwAAAAAAAAAAAAgQQAAIEEAACBBlGgWSwOFlGgkdJRSlIwIbG93X3JlcHKUjAUtMTAuMJSMCWhpZ2hfcmVwcpSMBDEwLjCUjApfbnBfcmFuZG9tlE51YowMZGVzaXJlZF9nb2FslGgNKYGUfZQoaBBoFmgZaBwolgMAAAAAAAAAAQEBlGggSwOFlGgkdJRSlGgnaBwolgMAAAAAAAAAAQEBlGggSwOFlGgkdJRSlGgsSwOFlGguaBwolgwAAAAAAAAAAAAgwQAAIMEAACDBlGgWSwOFlGgkdJRSlGgzaBwolgwAAAAAAAAAAAAgQQAAIEEAACBBlGgWSwOFlGgkdJRSlGg4jAUtMTAuMJRoOowEMTAuMJRoPE51YowLb2JzZXJ2YXRpb26UaA0pgZR9lChoEGgWaBloHCiWBgAAAAAAAAABAQEBAQGUaCBLBoWUaCR0lFKUaCdoHCiWBgAAAAAAAAABAQEBAQGUaCBLBoWUaCR0lFKUaCxLBoWUaC5oHCiWGAAAAAAAAAAAACDBAAAgwQAAIMEAACDBAAAgwQAAIMGUaBZLBoWUaCR0lFKUaDNoHCiWGAAAAAAAAAAAACBBAAAgQQAAIEEAACBBAAAgQQAAIEGUaBZLBoWUaCR0lFKUaDiMBS0xMC4wlGg6jAQxMC4wlGg8TnVidWgsTmgQTmg8TnViLg==", "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True]", "bounded_above": "[ True  True  True]", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.6.56+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Nov 10 10:07:59 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.1.0", "PyTorch": "2.5.1+cu121", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "Gymnasium": "0.29.0", "OpenAI Gym": "0.25.2"}}

results.json

@@ -1 +1 @@
-{"mean_reward": -19.02940659970045, "std_reward": 3.496120750355281, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-19T02:35:07.617080"}
+{"mean_reward": -0.2050792294088751, "std_reward": 0.09035168785831214, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-19T03:21:22.992393"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:812dfb7b7e569445ccdf4ea5192af66b858e155baa1144f99e7aeb1d24cb4bff
-size 2636
+oid sha256:b665713f0cea020233ef36ca25d6df7350f369b702d126742b3d5f728be3aeb9
+size 2623