Upload PPO Acrobot-v1 trained agent

Acrobot-v1.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28a3d7a95ae6663add526911d9c16d71ea3d053601d17512b9804dfa565aac83
-size 147904
+oid sha256:55f4a6e50750e292a6ea5f0b4a831ec85d52f462d58bd99167f8d757a44ecdfa
+size 148354

Acrobot-v1/data

@@ -4,34 +4,34 @@
         ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
         "__module__": "stable_baselines3.common.policies",
         "__doc__": "\n    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\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: Features extractor to use.\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 ActorCriticPolicy.__init__ at 0x78753edbf560>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78753edbf600>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78753edbf6a0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78753edbf740>",
-        "_build": "<function ActorCriticPolicy._build at 0x78753edbf7e0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x78753edbf880>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x78753edbf920>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78753edbf9c0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x78753edbfa60>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78753edbfb00>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78753edbfba0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x78753edbfc40>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7d7fa3e9c720>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d7fa3e9c7c0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d7fa3e9c860>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d7fa3e9c900>",
+        "_build": "<function ActorCriticPolicy._build at 0x7d7fa3e9c9a0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7d7fa3e9ca40>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d7fa3e9cae0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d7fa3e9cb80>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7d7fa3e9cc20>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d7fa3e9ccc0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d7fa3e9cd60>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d7fa3e9ce00>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x78753edab640>"
+        "_abc_impl": "<_abc._abc_data object at 0x7d7fa3feb0c0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 409600,
-    "_total_timesteps": 400000,
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1762559151258994773,
+    "start_time": 1763162189171618550,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -41,17 +41,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.02400000000000002,
+    "_current_progress_remaining": -0.015808000000000044,
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 100,
+    "_n_updates": 248,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -89,14 +89,14 @@
         "__module__": "stable_baselines3.common.buffers",
         "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}",
         "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\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 gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ",
-        "__init__": "<function RolloutBuffer.__init__ at 0x78753ed3c400>",
-        "reset": "<function RolloutBuffer.reset at 0x78753ed3c4a0>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x78753ed3c540>",
-        "add": "<function RolloutBuffer.add at 0x78753ed3c680>",
-        "get": "<function RolloutBuffer.get at 0x78753ed3c720>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x78753ed3c7c0>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x7d7fa3e214e0>",
+        "reset": "<function RolloutBuffer.reset at 0x7d7fa3e21580>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7d7fa3e21620>",
+        "add": "<function RolloutBuffer.add at 0x7d7fa3e21760>",
+        "get": "<function RolloutBuffer.get at 0x7d7fa3e21800>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x7d7fa3e218a0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x78753f1678c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7d7fa3f1d180>"
     },
     "rollout_buffer_kwargs": {},
     "batch_size": 64,

Acrobot-v1/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8abdba758307d8a23f165fd6636df729392fb36ba56d4cc6f4df457d1a09a5f6
-size 85815
+oid sha256:110ebb6b32903c4749a5bbed02b9784b5431ae99a8aa0d339584c56624dfb841
+size 86135

Acrobot-v1/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c68796634bd4499457b10363766ab600d467fe5c57cf9fcd7a068de8fe89eea
-size 42687
+oid sha256:f7365796e4a0d37ab2079c50fc2f55570b18cd0c8484ef640be8245349aa3677
+size 42815

Acrobot-v1/system_info.txt

@@ -2,7 +2,7 @@
 - Python: 3.12.12
 - Stable-Baselines3: 2.7.0
 - PyTorch: 2.8.0+cu126
-- GPU Enabled: False
+- GPU Enabled: True
 - Numpy: 2.0.2
 - Cloudpickle: 3.1.2
 - Gymnasium: 1.2.2

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Acrobot-v1
     metrics:
     - type: mean_reward
-      value: -96.90 +/- 62.67
+      value: -79.90 +/- 6.36
       name: mean_reward
       verified: false
 ---

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    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\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: Features extractor to use.\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 ActorCriticPolicy.__init__ at 0x78753edbf560>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78753edbf600>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78753edbf6a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78753edbf740>", "_build": "<function ActorCriticPolicy._build at 0x78753edbf7e0>", "forward": "<function ActorCriticPolicy.forward at 0x78753edbf880>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x78753edbf920>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78753edbf9c0>", "_predict": "<function ActorCriticPolicy._predict at 0x78753edbfa60>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78753edbfb00>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78753edbfba0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x78753edbfc40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78753edab640>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 409600, "_total_timesteps": 400000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1762559151258994773, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.02400000000000002, "_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": 100, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [6], "low": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]", "bounded_below": "[ True  True  True  True  True  True]", "high": "[ 1.        1.        1.        1.       12.566371 28.274334]", "bounded_above": "[ True  True  True  True  True  True]", "low_repr": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]", "high_repr": "[ 1.        1.        1.        1.       12.566371 28.274334]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwFZHR5cGWUjAVudW1weZSMBWR0eXBllJOUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijAFulIwWbnVtcHkuX2NvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlGgLQwgDAAAAAAAAAJSGlFKUjAVzdGFydJRoEWgLQwgAAAAAAAAAAJSGlFKUjAZfc2hhcGWUKYwKX25wX3JhbmRvbZROdWIu", "dtype": "int64", "n": "3", "start": "0", "_shape": [], "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}", "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\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 gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ", "__init__": "<function RolloutBuffer.__init__ at 0x78753ed3c400>", "reset": "<function RolloutBuffer.reset at 0x78753ed3c4a0>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x78753ed3c540>", "add": "<function RolloutBuffer.add at 0x78753ed3c680>", "get": "<function RolloutBuffer.get at 0x78753ed3c720>", "_get_samples": "<function RolloutBuffer._get_samples at 0x78753ed3c7c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78753f1678c0>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/yZmZmZmZmnNic2Iu", "value_schedule": "ConstantSchedule(val=0.2)"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/M6kqMFUyYXNic2Iu", "value_schedule": "ConstantSchedule(val=0.0003)"}, "system_info": {"OS": "Linux-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct  2 10:42:05 UTC 2025", "Python": "3.12.12", "Stable-Baselines3": "2.7.0", "PyTorch": "2.8.0+cu126", "GPU Enabled": "False", "Numpy": "2.0.2", "Cloudpickle": "3.1.2", "Gymnasium": "1.2.2", "OpenAI Gym": "0.25.2"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    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\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: Features extractor to use.\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 ActorCriticPolicy.__init__ at 0x7d7fa3e9c720>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d7fa3e9c7c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d7fa3e9c860>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d7fa3e9c900>", "_build": "<function ActorCriticPolicy._build at 0x7d7fa3e9c9a0>", "forward": "<function ActorCriticPolicy.forward at 0x7d7fa3e9ca40>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d7fa3e9cae0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d7fa3e9cb80>", "_predict": "<function ActorCriticPolicy._predict at 0x7d7fa3e9cc20>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d7fa3e9ccc0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d7fa3e9cd60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d7fa3e9ce00>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d7fa3feb0c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1763162189171618550, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV9gEAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWgAEAAAAAAADqwW0/gtC9vhe5Kj+/wj4/HL+dvtPmhz/nQzA/2KY5P2JSRT9rGCO/FX3sP3V9XMBQ4zS/kCY1Pzx1eLx3+H+/5DyeP8MGjL/Lxxy/KWBKP2PmHD9xSEq/+d4nvteXuUDIEqi97yJ/vwj1Sb+yUR0/YA1YQHud+L+oK2i9o5Z/P3A9dz+ayoQ+sPsfv8qUzr8gqnY/UAGJPjsqej9PYlm+mLFcP82WI8CwRHw/VDQuvhI09T6Yu2A/y3ZsQPn3sMAw1mk+Yzx5PwGATz5jsHo/+3H5Pw36Q8Bh6nc/zk5/PnSCXz+vovm+s2mcPjKvFb/yEHo/5jFbvswdJb27yn8/0MqaQH7NhcD0J3m/ljFrvg/Gfr9ROMg9KozMv3Nvi0AmUnS+RZt4vz/7f79XWkW8kmDUvzP+xL/x1H8/d3QUveobfz+mt6o9CN0Ovu4ALj+kOsg+tZxrv7KDQL80vig/bz4IQLcSmb/1/xY/frlOvyNHbT80M8C+K5BZwKi71UCUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSxBLBoaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_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": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [6], "low": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]", "bounded_below": "[ True  True  True  True  True  True]", "high": "[ 1.        1.        1.        1.       12.566371 28.274334]", "bounded_above": "[ True  True  True  True  True  True]", "low_repr": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]", "high_repr": "[ 1.        1.        1.        1.       12.566371 28.274334]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwFZHR5cGWUjAVudW1weZSMBWR0eXBllJOUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijAFulIwWbnVtcHkuX2NvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlGgLQwgDAAAAAAAAAJSGlFKUjAVzdGFydJRoEWgLQwgAAAAAAAAAAJSGlFKUjAZfc2hhcGWUKYwKX25wX3JhbmRvbZROdWIu", "dtype": "int64", "n": "3", "start": "0", "_shape": [], "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}", "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\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 gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ", "__init__": "<function RolloutBuffer.__init__ at 0x7d7fa3e214e0>", "reset": "<function RolloutBuffer.reset at 0x7d7fa3e21580>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7d7fa3e21620>", "add": "<function RolloutBuffer.add at 0x7d7fa3e21760>", "get": "<function RolloutBuffer.get at 0x7d7fa3e21800>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7d7fa3e218a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d7fa3f1d180>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/yZmZmZmZmnNic2Iu", "value_schedule": "ConstantSchedule(val=0.2)"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/M6kqMFUyYXNic2Iu", "value_schedule": "ConstantSchedule(val=0.0003)"}, "system_info": {"OS": "Linux-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct  2 10:42:05 UTC 2025", "Python": "3.12.12", "Stable-Baselines3": "2.7.0", "PyTorch": "2.8.0+cu126", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.2", "Gymnasium": "1.2.2", "OpenAI Gym": "0.25.2"}}

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88c1fb40c1cc9969ec073efd87a9977d43396d05cbf0c9283f14ad7d0ec0c508
-size 701315
+oid sha256:833d5cf48b4317b5c6a44acfb9d6d8719e6332e44482c9f4737cf1d730ff3bc5
+size 706768

results.json

@@ -1 +1 @@
-{"mean_reward": -96.9, "std_reward": 62.67288089756207, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-07T23:51:07.252532"}
+{"mean_reward": -79.9, "std_reward": 6.363175307973213, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-14T23:29:28.139290"}