Test commit

CartPole-v1.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72f9951ce346dc5d27dbe3923bb6156c00fd50754509989be367ad55a7b54aca
-size 102088
+oid sha256:0af709e7c3395afaa359ca0753e225adbf1b0348bb61ebd75551f67837619436
+size 101096

CartPole-v1/data

@@ -5,18 +5,18 @@
         "__module__": "stable_baselines3.common.policies",
         "__firstlineno__": 416,
         "__doc__": "\nPolicy class for actor-critic algorithms (has both policy and value prediction).\nUsed 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 0x7f3d605e0220>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3d605e02c0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3d605e0360>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3d605e0400>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f3d605e04a0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f3d605e0540>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f3d605e05e0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3d605e0680>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f3d605e0720>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3d605e07c0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3d605e0860>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3d605e0900>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fa00d5c8220>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa00d5c82c0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa00d5c8360>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa00d5c8400>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fa00d5c84a0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fa00d5c8540>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fa00d5c85e0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa00d5c8680>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fa00d5c8720>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa00d5c87c0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa00d5c8860>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa00d5c8900>",
         "__static_attributes__": [
             "action_dist",
             "action_net",
@@ -37,7 +37,7 @@
             "vf_features_extractor"
         ],
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f3d6d567680>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fa00d5ba140>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -55,12 +55,12 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1742141394087891216,
+    "start_time": 1742143064190480182,
     "learning_rate": 0.0007,
-    "tensorboard_log": "runs/gvayevmx",
+    "tensorboard_log": "runs/y4ta772v",
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVhgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAaXUi+1Jhhvxoax71l1Kc+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwSGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVhgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAABjTd+9QpsvPjByYD2EQGM8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwSGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -74,7 +74,7 @@
     "_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'>",
@@ -119,12 +119,12 @@
         "__firstlineno__": 343,
         "__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__": "\nRollout buffer used in on-policy algorithms like A2C/PPO.\nIt corresponds to ``buffer_size`` transitions collected\nusing the current policy.\nThis experience will be discarded after the policy update.\nIn order to use PPO objective, we also store the current value of each state\nand the log probability of each taken action.\n\nThe term rollout here refers to the model-free notion and should not\nbe used with the concept of rollout used in model-based RL or planning.\nHence, 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 0x7f3d6b616fc0>",
-        "reset": "<function RolloutBuffer.reset at 0x7f3d6b617060>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7f3d6b617100>",
-        "add": "<function RolloutBuffer.add at 0x7f3d6b617240>",
-        "get": "<function RolloutBuffer.get at 0x7f3d6b6172e0>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x7f3d6b617380>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x7fa018696fc0>",
+        "reset": "<function RolloutBuffer.reset at 0x7fa018697060>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7fa018697100>",
+        "add": "<function RolloutBuffer.add at 0x7fa018697240>",
+        "get": "<function RolloutBuffer.get at 0x7fa0186972e0>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x7fa018697380>",
         "__static_attributes__": [
             "actions",
             "advantages",
@@ -140,7 +140,7 @@
             "values"
         ],
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f3d6b60f340>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fa0186a0500>"
     },
     "rollout_buffer_kwargs": {},
     "normalize_advantage": false,

CartPole-v1/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eed8caae2e4de47cfb8f8957913b00839bd44f226fadf6d0c098d4198364431
+oid sha256:ecd9da94a4246c219e1388d69edf0651f2039b13c6b53da483420dbef7261de8
 size 43406

CartPole-v1/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:960eb72b009c8c2cee10d8f093b03d93ccb220910a2c0b6cf6bed9298f2da249
+oid sha256:a071464ea6995f3909568965d18faab569861bd26f328f735e09d6e2cd2f1d71
 size 41074

README.md

@@ -16,7 +16,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 174.00 +/- 35.23
+      value: 130.20 +/- 17.10
       name: mean_reward
       verified: false
 ---

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__firstlineno__": 416, "__doc__": "\nPolicy class for actor-critic algorithms (has both policy and value prediction).\nUsed 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 0x7f3d605e0220>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3d605e02c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3d605e0360>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3d605e0400>", "_build": "<function ActorCriticPolicy._build at 0x7f3d605e04a0>", "forward": "<function ActorCriticPolicy.forward at 0x7f3d605e0540>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f3d605e05e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3d605e0680>", "_predict": "<function ActorCriticPolicy._predict at 0x7f3d605e0720>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3d605e07c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3d605e0860>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3d605e0900>", "__static_attributes__": ["action_dist", "action_net", "activation_fn", "dist_kwargs", "features_dim", "features_extractor", "log_std", "log_std_init", "mlp_extractor", "net_arch", "optimizer", "ortho_init", "pi_features_extractor", "share_features_extractor", "use_sde", "value_net", "vf_features_extractor"], "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f3d6d567680>"}, "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": 10000, "_total_timesteps": 10000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1742141394087891216, "learning_rate": 0.0007, "tensorboard_log": "runs/gvayevmx", "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAaXUi+1Jhhvxoax71l1Kc+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwSGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_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": 2000, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [4], "low": "[-4.8               -inf -0.41887903        -inf]", "bounded_below": "[ True False  True False]", "high": "[4.8               inf 0.41887903        inf]", "bounded_above": "[ True False  True False]", "low_repr": "[-4.8               -inf -0.41887903        -inf]", "high_repr": "[4.8               inf 0.41887903        inf]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAIAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "n": "2", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__firstlineno__": 343, "__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__": "\nRollout buffer used in on-policy algorithms like A2C/PPO.\nIt corresponds to ``buffer_size`` transitions collected\nusing the current policy.\nThis experience will be discarded after the policy update.\nIn order to use PPO objective, we also store the current value of each state\nand the log probability of each taken action.\n\nThe term rollout here refers to the model-free notion and should not\nbe used with the concept of rollout used in model-based RL or planning.\nHence, 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 0x7f3d6b616fc0>", "reset": "<function RolloutBuffer.reset at 0x7f3d6b617060>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7f3d6b617100>", "add": "<function RolloutBuffer.add at 0x7f3d6b617240>", "get": "<function RolloutBuffer.get at 0x7f3d6b6172e0>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7f3d6b617380>", "__static_attributes__": ["actions", "advantages", "episode_starts", "full", "gae_lambda", "gamma", "generator_ready", "log_probs", "observations", "returns", "rewards", "values"], "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f3d6b60f340>"}, "rollout_buffer_kwargs": {}, "normalize_advantage": false, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.4.0-150600.23.42-default-x86_64-with-glibc2.38 # 1 SMP PREEMPT_DYNAMIC Fri Mar  7 09:53:00 UTC 2025 (7bf6ecd)", "Python": "3.13.2", "Stable-Baselines3": "2.5.0", "PyTorch": "2.6.0+cu124", "GPU Enabled": "False", "Numpy": "2.2.3", "Cloudpickle": "3.1.1", "Gymnasium": "1.0.0"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__firstlineno__": 416, "__doc__": "\nPolicy class for actor-critic algorithms (has both policy and value prediction).\nUsed 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 0x7fa00d5c8220>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa00d5c82c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa00d5c8360>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa00d5c8400>", "_build": "<function ActorCriticPolicy._build at 0x7fa00d5c84a0>", "forward": "<function ActorCriticPolicy.forward at 0x7fa00d5c8540>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fa00d5c85e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa00d5c8680>", "_predict": "<function ActorCriticPolicy._predict at 0x7fa00d5c8720>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa00d5c87c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa00d5c8860>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa00d5c8900>", "__static_attributes__": ["action_dist", "action_net", "activation_fn", "dist_kwargs", "features_dim", "features_extractor", "log_std", "log_std_init", "mlp_extractor", "net_arch", "optimizer", "ortho_init", "pi_features_extractor", "share_features_extractor", "use_sde", "value_net", "vf_features_extractor"], "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fa00d5ba140>"}, "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": 10000, "_total_timesteps": 10000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1742143064190480182, "learning_rate": 0.0007, "tensorboard_log": "runs/y4ta772v", "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAABjTd+9QpsvPjByYD2EQGM8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwSGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_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": 2000, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [4], "low": "[-4.8               -inf -0.41887903        -inf]", "bounded_below": "[ True False  True False]", "high": "[4.8               inf 0.41887903        inf]", "bounded_above": "[ True False  True False]", "low_repr": "[-4.8               -inf -0.41887903        -inf]", "high_repr": "[4.8               inf 0.41887903        inf]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAIAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "n": "2", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__firstlineno__": 343, "__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__": "\nRollout buffer used in on-policy algorithms like A2C/PPO.\nIt corresponds to ``buffer_size`` transitions collected\nusing the current policy.\nThis experience will be discarded after the policy update.\nIn order to use PPO objective, we also store the current value of each state\nand the log probability of each taken action.\n\nThe term rollout here refers to the model-free notion and should not\nbe used with the concept of rollout used in model-based RL or planning.\nHence, 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 0x7fa018696fc0>", "reset": "<function RolloutBuffer.reset at 0x7fa018697060>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7fa018697100>", "add": "<function RolloutBuffer.add at 0x7fa018697240>", "get": "<function RolloutBuffer.get at 0x7fa0186972e0>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7fa018697380>", "__static_attributes__": ["actions", "advantages", "episode_starts", "full", "gae_lambda", "gamma", "generator_ready", "log_probs", "observations", "returns", "rewards", "values"], "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fa0186a0500>"}, "rollout_buffer_kwargs": {}, "normalize_advantage": false, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.4.0-150600.23.42-default-x86_64-with-glibc2.38 # 1 SMP PREEMPT_DYNAMIC Fri Mar  7 09:53:00 UTC 2025 (7bf6ecd)", "Python": "3.13.2", "Stable-Baselines3": "2.5.0", "PyTorch": "2.6.0+cu124", "GPU Enabled": "False", "Numpy": "2.2.3", "Cloudpickle": "3.1.1", "Gymnasium": "1.0.0"}}

results.json

@@ -1 +1 @@
-{"mean_reward": 174.0, "std_reward": 35.230668458035254, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-16T17:10:15.839261"}
+{"mean_reward": 130.2, "std_reward": 17.104385402580238, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-16T17:38:22.528497"}