Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v2
     metrics:
     - type: mean_reward
-      value: -8.05 +/- 1.31
+      value: -8.07 +/- 2.78
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c0548904a3da11db2c0d09550c55065c886ce947e7ff2c3c90d079e21667949
-size 102605
+oid sha256:2ca8b2e17132968ed6364f7d794a6636845b78a38b5cf647b6fb81dd7d0edbaf
+size 103786

a2c-PandaReachDense-v2/data

@@ -19,12 +19,12 @@
             "weight_decay": 0
         }
     },
-    "num_timesteps": 20,
-    "_total_timesteps": 2,
+    "num_timesteps": 1000,
+    "_total_timesteps": 1000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1686818197887586799,
+    "start_time": 1686818510747918793,
     "learning_rate": 0.0007,
     "tensorboard_log": null,
     "lr_schedule": {
@@ -33,36 +33,36 @@
     },
     "_last_obs": {
         ":type:": "<class 'collections.OrderedDict'>",
-        ":serialized:": "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",
-        "achieved_goal": "[[-0.7642531  -2.0825026  -0.52186227]\n [ 0.37361467  1.5651536  -2.220405  ]\n [-2.0635672   1.6714268  -1.4163154 ]\n [ 0.914937   -2.40183     2.013523  ]]",
-        "desired_goal": "[[ 0.43507567 -1.7014273  -1.100557  ]\n [ 1.4314716   0.68557584  1.4019233 ]\n [-0.84086454  0.2652346  -0.7737618 ]\n [-1.025695    0.7506233   0.47241485]]",
-        "observation": "[[-0.7642531  -2.0825026  -0.52186227 -0.16579106 -1.0118539   0.58833253]\n [ 0.37361467  1.5651536  -2.220405    0.43424243  0.31327245 -1.8497232 ]\n [-2.0635672   1.6714268  -1.4163154  -3.349212    0.74049985 -0.5833983 ]\n [ 0.914937   -2.40183     2.013523   -0.05248883 -1.1717901  -0.8183713 ]]"
+        ":serialized:": "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",
+        "achieved_goal": "[[ 0.700315  -0.2241695  1.2144481]\n [ 0.700315  -0.2241695  1.2144481]\n [ 0.700315  -0.2241695  1.2144481]\n [ 0.700315  -0.2241695  1.2144481]]",
+        "desired_goal": "[[-1.773888    1.2115036  -0.19568753]\n [ 1.9629254  -2.0465438   0.05856952]\n [ 0.56196946 -1.3633636  -1.4713022 ]\n [-0.05143945  0.9908023   0.62950605]]",
+        "observation": "[[ 0.700315   -0.2241695   1.2144481   0.09523885 -0.03099636  0.08114898]\n [ 0.700315   -0.2241695   1.2144481   0.09523885 -0.03099636  0.08114898]\n [ 0.700315   -0.2241695   1.2144481   0.09523885 -0.03099636  0.08114898]\n [ 0.700315   -0.2241695   1.2144481   0.09523885 -0.03099636  0.08114898]]"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": "[[-0.02454872 -0.14601074  0.00751497]\n [ 0.05686267  0.1185339   0.2719398 ]\n [-0.12880053  0.0719487   0.04204581]\n [-0.14390226  0.12574293  0.1737232 ]]",
+        "desired_goal": "[[-0.05967258  0.07569756  0.20409408]\n [ 0.12655859 -0.006049    0.13499647]\n [-0.00378556  0.0546757   0.07921519]\n [-0.14325608 -0.04585527  0.24123725]]",
         "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": -9.0,
+    "_current_progress_remaining": 0.0,
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 1,
+    "_n_updates": 50,
     "n_steps": 5,
     "gamma": 0.99,
     "gae_lambda": 1.0,

a2c-PandaReachDense-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8c12104d75b1a44448e7e5308db1874681ef066dcf4f62f4c1e28e7109ef09b
+oid sha256:1e7db2c1a4c82ce891c4ad5025df162c0b6d6d417365ef83887f9207ef74cf00
 size 44734

a2c-PandaReachDense-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ad86cec0efadcb36f18fded26936f219ae3fab779b95cd195fb17ecf325cbf3
+oid sha256:81e30db40d10f28739ce230f0a0e445bf74ad29a5e684a58025b08fd5dc551e4
 size 46014

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 0x7f5ec1e4eef0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f5ec1e594c0>"}, "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": 20, "_total_timesteps": 2, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1686818197887586799, "learning_rate": 0.0007, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[-0.7642531  -2.0825026  -0.52186227]\n [ 0.37361467  1.5651536  -2.220405  ]\n [-2.0635672   1.6714268  -1.4163154 ]\n [ 0.914937   -2.40183     2.013523  ]]", "desired_goal": "[[ 0.43507567 -1.7014273  -1.100557  ]\n [ 1.4314716   0.68557584  1.4019233 ]\n [-0.84086454  0.2652346  -0.7737618 ]\n [-1.025695    0.7506233   0.47241485]]", "observation": "[[-0.7642531  -2.0825026  -0.52186227 -0.16579106 -1.0118539   0.58833253]\n [ 0.37361467  1.5651536  -2.220405    0.43424243  0.31327245 -1.8497232 ]\n [-2.0635672   1.6714268  -1.4163154  -3.349212    0.74049985 -0.5833983 ]\n [ 0.914937   -2.40183     2.013523   -0.05248883 -1.1717901  -0.8183713 ]]"}, "_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": "[[-0.02454872 -0.14601074  0.00751497]\n [ 0.05686267  0.1185339   0.2719398 ]\n [-0.12880053  0.0719487   0.04204581]\n [-0.14390226  0.12574293  0.1737232 ]]", "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": -9.0, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1, "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 'gym.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('desired_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('observation', Box([-10. -10. -10. -10. -10. -10.], [10. 10. 10. 10. 10. 10.], (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "bounded_below": "[ True  True  True]", "bounded_above": "[ True  True  True]", "_np_random": null}, "n_envs": 4, "system_info": {"OS": "Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "1.8.0", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
+{"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 0x7f5ec1e4eef0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f5ec1e594c0>"}, "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": 1000, "_total_timesteps": 1000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1686818510747918793, "learning_rate": 0.0007, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 0.700315  -0.2241695  1.2144481]\n [ 0.700315  -0.2241695  1.2144481]\n [ 0.700315  -0.2241695  1.2144481]\n [ 0.700315  -0.2241695  1.2144481]]", "desired_goal": "[[-1.773888    1.2115036  -0.19568753]\n [ 1.9629254  -2.0465438   0.05856952]\n [ 0.56196946 -1.3633636  -1.4713022 ]\n [-0.05143945  0.9908023   0.62950605]]", "observation": "[[ 0.700315   -0.2241695   1.2144481   0.09523885 -0.03099636  0.08114898]\n [ 0.700315   -0.2241695   1.2144481   0.09523885 -0.03099636  0.08114898]\n [ 0.700315   -0.2241695   1.2144481   0.09523885 -0.03099636  0.08114898]\n [ 0.700315   -0.2241695   1.2144481   0.09523885 -0.03099636  0.08114898]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": "[[-0.05967258  0.07569756  0.20409408]\n [ 0.12655859 -0.006049    0.13499647]\n [-0.00378556  0.0546757   0.07921519]\n [-0.14325608 -0.04585527  0.24123725]]", "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": 50, "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 'gym.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('desired_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('observation', Box([-10. -10. -10. -10. -10. -10.], [10. 10. 10. 10. 10. 10.], (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "bounded_below": "[ True  True  True]", "bounded_above": "[ True  True  True]", "_np_random": null}, "n_envs": 4, "system_info": {"OS": "Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "1.8.0", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}

results.json

@@ -1 +1 @@
-{"mean_reward": -8.048635559529066, "std_reward": 1.3111847917691677, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-15T08:36:41.679664"}
+{"mean_reward": -8.072087429836392, "std_reward": 2.782124035124461, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-15T08:42:00.149769"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec6d7df09da7fa80db51137a0932d1ea672cc205e5324ebd38399d16d7a9ab49
+oid sha256:69051bb1a91ed33da076568b12360d76c0a0428606208f364fad37d9c4ba7efc
 size 2387