Test commit

Browse files

Files changed (6) hide show

a2c_sb3_cartpole.zip +2 -2
a2c_sb3_cartpole/data +24 -24
a2c_sb3_cartpole/policy.optimizer.pth +1 -1
a2c_sb3_cartpole/policy.pth +1 -1
config.json +1 -1
results.json +1 -1

a2c_sb3_cartpole.zip CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7601cf5e434ecddcf8867c05d26729f31ff1a52ccf4679063655c302579b0a61
-size 98379

 version https://git-lfs.github.com/spec/v1
+oid sha256:fea452ec784967bba920cd1da85a3a3a154e162a8af13c9734203395b44465dc
+size 98378

a2c_sb3_cartpole/data CHANGED Viewed

@@ -4,20 +4,20 @@
         ":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 0x1213d2980>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x1213d2a20>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x1213d2ac0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x1213d2b60>",
-        "_build": "<function ActorCriticPolicy._build at 0x1213d2c00>",
-        "forward": "<function ActorCriticPolicy.forward at 0x1213d2ca0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x1213d2d40>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x1213d2de0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x1213d2e80>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x1213d2f20>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x1213d2fc0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x1213d3060>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x1213d5340>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -35,12 +35,12 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1773225876008582000,
     "learning_rate": 0.0007,
-    "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAJplsb1+cjy+6pPDu7AMgT6UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -54,7 +54,7 @@
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
@@ -98,14 +98,14 @@
         "__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 0x1178e3f60>",
-        "reset": "<function RolloutBuffer.reset at 0x1178e4040>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x1178e40e0>",
-        "add": "<function RolloutBuffer.add at 0x1178e4220>",
-        "get": "<function RolloutBuffer.get at 0x1178e42c0>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x1178e4360>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x117870d00>"
     },
     "rollout_buffer_kwargs": {},
     "normalize_advantage": false,

         ":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 0x12ea4ab60>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x12ea4ac00>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x12ea4aca0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x12ea4ad40>",
+        "_build": "<function ActorCriticPolicy._build at 0x12ea4ade0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x12ea4ae80>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x12ea4af20>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x12ea4afc0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x12ea4b060>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x12ea4b100>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x12ea4b1a0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x12ea4b240>",
         "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x12ea50e40>"
     },
     "verbose": 1,
     "policy_kwargs": {
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
+    "start_time": 1773226702308490000,
     "learning_rate": 0.0007,
+    "tensorboard_log": "runs/kp8vtbbp",
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAOLLD7vznvA8CBOXvIK4Fr2UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         "__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 0x124f5c180>",
+        "reset": "<function RolloutBuffer.reset at 0x124f5c220>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x124f5c2c0>",
+        "add": "<function RolloutBuffer.add at 0x124f5c400>",
+        "get": "<function RolloutBuffer.get at 0x124f5c4a0>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x124f5c540>",
         "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x124ee8b40>"
     },
     "rollout_buffer_kwargs": {},
     "normalize_advantage": false,

a2c_sb3_cartpole/policy.optimizer.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d814b5e415743d5fb139a94357dde7b04e5f8ea9bfc1c8539296ca63bb3b6754
 size 40370

 version https://git-lfs.github.com/spec/v1
+oid sha256:4fab67fc23656bd11186ed03ec74f0464dac52845a2506256ffbe9b6f9dfb555
 size 40370

a2c_sb3_cartpole/policy.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0f593b7d9f55e8013aab81fb031f0b03a2e450a44432659772ff58c450e762d
 size 41074

 version https://git-lfs.github.com/spec/v1
+oid sha256:60209cd7584139b0c10266ae9c2550c1b02fb51f20848ceab787b763dbe1dd9f
 size 41074

config.json CHANGED Viewed

@@ -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 0x1213d2980>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x1213d2a20>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x1213d2ac0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x1213d2b60>", "_build": "<function ActorCriticPolicy._build at 0x1213d2c00>", "forward": "<function ActorCriticPolicy.forward at 0x1213d2ca0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x1213d2d40>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x1213d2de0>", "_predict": "<function ActorCriticPolicy._predict at 0x1213d2e80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x1213d2f20>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x1213d2fc0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x1213d3060>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x1213d5340>"}, "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": 100000, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1773225876008582000, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAJplsb1+cjy+6pPDu7AMgT6UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_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": 10000, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAgAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "2", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 10, "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", "__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 0x1178e3f60>", "reset": "<function RolloutBuffer.reset at 0x1178e4040>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x1178e40e0>", "add": "<function RolloutBuffer.add at 0x1178e4220>", "get": "<function RolloutBuffer.get at 0x1178e42c0>", "_get_samples": "<function RolloutBuffer._get_samples at 0x1178e4360>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x117870d00>"}, "rollout_buffer_kwargs": {}, "normalize_advantage": false, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "macOS-15.7.4-x86_64-i386-64bit Darwin Kernel Version 24.6.0: Mon Jan 19 22:00:10 PST 2026; root:xnu-11417.140.69.708.3~1/RELEASE_X86_64", "Python": "3.11.11", "Stable-Baselines3": "2.4.1", "PyTorch": "2.2.2", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.1.2", "Gymnasium": "1.0.0"}}

+ {"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 0x12ea4ab60>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x12ea4ac00>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x12ea4aca0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x12ea4ad40>", "_build": "<function ActorCriticPolicy._build at 0x12ea4ade0>", "forward": "<function ActorCriticPolicy.forward at 0x12ea4ae80>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x12ea4af20>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x12ea4afc0>", "_predict": "<function ActorCriticPolicy._predict at 0x12ea4b060>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x12ea4b100>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x12ea4b1a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x12ea4b240>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x12ea50e40>"}, "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": 100000, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1773226702308490000, "learning_rate": 0.0007, "tensorboard_log": "runs/kp8vtbbp", "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAOLLD7vznvA8CBOXvIK4Fr2UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_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:": "gAWVDAwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQFdAAAAAAACMAWyUS12MAXSUR0BfjN6kZaV2dX2UKGgGR0BhQAAAAAAAaAdLimgIR0BfmmUbDMvAdX2UKGgGR0BjYAAAAAAAaAdLm2gIR0BfqG5hBqsVdX2UKGgGR0BRwAAAAAAAaAdLR2gIR0BfrlxKg7HRdX2UKGgGR0BfwAAAAAAAaAdLf2gIR0BfuYf0VafSdX2UKGgGR0BewAAAAAAAaAdLe2gIR0BfxzByjpLVdX2UKGgGR0BOgAAAAAAAaAdLPWgIR0BfzMrupjtpdX2UKGgGR0BhQAAAAAAAaAdLimgIR0Bf3YAn2IwedX2UKGgGR0BZAAAAAAAAaAdLZGgIR0Bf5u4LCvX9dX2UKGgGR0BYwAAAAAAAaAdLY2gIR0Bf7xGMGX5WdX2UKGgGR0BVwAAAAAAAaAdLV2gIR0Bf92Gh24d7dX2UKGgGR0BgwAAAAAAAaAdLhmgIR0BgBEg0TDfndX2UKGgGR0BfwAAAAAAAaAdLf2gIR0BgC0h5gPVedX2UKGgGR0BeQAAAAAAAaAdLeWgIR0BgEUSf16E8dX2UKGgGR0BjAAAAAAAAaAdLmGgIR0BgGXxnWattdX2UKGgGR0BhgAAAAAAAaAdLjGgIR0BgH2W+oLofdX2UKGgGR0BrgAAAAAAAaAdL3GgIR0BgKsBfa6BidX2UKGgGR0BlwAAAAAAAaAdLrmgIR0BgM0QTVUdadX2UKGgGR0Bu4AAAAAAAaAdL92gIR0BgP27UXpGGdX2UKGgGR0BegAAAAAAAaAdLemgIR0BgRVG3F1jidX2UKGgGR0BYQAAAAAAAaAdLYWgIR0BgSVCE6DGtdX2UKGgGR0BYgAAAAAAAaAdLYmgIR0BgTVdC3PRidX2UKGgGR0BgIAAAAAAAaAdLgWgIR0BgVERradtmdX2UKGgGR0BYgAAAAAAAaAdLYmgIR0BgWRDohY/3dX2UKGgGR0BkwAAAAAAAaAdLpmgIR0BgYJzPrv9cdX2UKGgGR0BgYAAAAAAAaAdLg2gIR0BgZn2Xb/OudX2UKGgGR0BqYAAAAAAAaAdL02gIR0Bgb9iYsunNdX2UKGgGR0BhQAAAAAAAaAdLimgIR0BgeEnqmj0udX2UKGgGR0BZAAAAAAAAaAdLZGgIR0BgfSy6cy31dX2UKGgGR0Bh4AAAAAAAaAdLj2gIR0Bgg6D0163RdX2UKGgGR0BkgAAAAAAAaAdLpGgIR0BgiojMV1wHdX2UKGgGR0BgAAAAAAAAaAdLgGgIR0BgkChg3LmqdX2UKGgGR0BjoAAAAAAAaAdLnWgIR0BgluZw4sErdX2UKGgGR0BnAAAAAAAAaAdLuGgIR0BgoCMUAT7EdX2UKGgGR0BbAAAAAAAAaAdLbGgIR0BgpxuIhyKfdX2UKGgGR0BVwAAAAAAAaAdLV2gIR0Bgq7jR2KVIdX2UKGgGR0BfgAAAAAAAaAdLfmgIR0Bgsx+tr9EUdX2UKGgGR0BggAAAAAAAaAdLhGgIR0Bgurk+5e7ddX2UKGgGR0BawAAAAAAAaAdLa2gIR0Bgv5BkZrHmdX2UKGgGR0BYgAAAAAAAaAdLYmgIR0BgxCw6hg3MdX2UKGgGR0BUwAAAAAAAaAdLU2gIR0BgxzGPxQSBdX2UKGgGR0BZQAAAAAAAaAdLZWgIR0Bgys/6fra/dX2UKGgGR0BWwAAAAAAAaAdLW2gIR0BgziV8kUsWdX2UKGgGR0BUQAAAAAAAaAdLUWgIR0Bg0Mx46fapdX2UKGgGR0BKAAAAAAAAaAdLNGgIR0Bg05SDRMN+dX2UKGgGR0BbQAAAAAAAaAdLbWgIR0Bg2JMi8nNQdX2UKGgGR0BdwAAAAAAAaAdLd2gIR0Bg3a7ZnL7odX2UKGgGR0Bg4AAAAAAAaAdLh2gIR0Bg40U/OdGzdX2UKGgGR0BgQAAAAAAAaAdLgmgIR0Bg6JDZ13dLdX2UKGgGR0BhoAAAAAAAaAdLjWgIR0Bg70580DU3dX2UKGgGR0BioAAAAAAAaAdLlWgIR0Bg94UpNKywdX2UKGgGR0BdgAAAAAAAaAdLdmgIR0Bg/Jg5R0lrdX2UKGgGR0BiYAAAAAAAaAdLk2gIR0BhA+/FirksdX2UKGgGR0BogAAAAAAAaAdLxGgIR0BhDNU4rBj4dX2UKGgGR0BmgAAAAAAAaAdLtGgIR0BhFMrAgxJvdX2UKGgGR0BqIAAAAAAAaAdL0WgIR0BhHmQCCBf8dX2UKGgGR0B0kAAAAAAAaAdNSQFoCEdAYTC5RTCLuXV9lChoBkdAcZAAAAAAAGgHTRkBaAhHQGFAFJg9eQd1fZQoaAZHQHEQAAAAAABoB00RAWgIR0BhTmlyimEXdX2UKGgGR0B0EAAAAAAAaAdNQQFoCEdAYV3JcPe54HV9lChoBkdAe3AAAAAAAGgHTbcBaAhHQGFz0iILw4N1fZQoaAZHQH9AAAAAAABoB030AWgIR0BhiSzJIUaidX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAYZ+1hLGrCHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQGGz4TTOPeZ1fZQoaAZHQH9AAAAAAABoB030AWgIR0BhyGj/MnqndX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAYd0h7mdRSHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQGH62qtHQQd1fZQoaAZHQH9AAAAAAABoB030AWgIR0BiD0052hZhdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAYievPC2tuHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQGI9Up3HJcR1fZQoaAZHQH9AAAAAAABoB030AWgIR0BiUZcxCY1HdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAYmfJNCZ4OnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQGKNDc/MW451fZQoaAZHQH9AAAAAAABoB030AWgIR0Bip0HdGiHqdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAYsLn/T9bYHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQGLoXyiEg4h1fZQoaAZHQH9AAAAAAABoB030AWgIR0BjBjfJmukldX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAYzB2K2rn1XV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQGNQIIv8IiV1fZQoaAZHQH9AAAAAAABoB030AWgIR0BjZ+aYu01JdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAY4HnIyTINnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQGOZEAHVwxZ1fZQoaAZHQH9AAAAAAABoB030AWgIR0BjsEFlkH2RdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAY8gcpb2US3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQGPfNlRP4211fZQoaAZHQH9AAAAAAABoB030AWgIR0Bj88ByS3b3dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAZA1GuLaVU3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQGQtPwEyLyd1fZQoaAZHQH9AAAAAAABoB030AWgIR0BkR1c2R7qqdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAZGP77bcoIHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQGSDNcnmaH91fZQoaAZHQH9AAAAAAABoB030AWgIR0BknXKr7wazdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAZLmiOearm3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQGTTuPV/c351fZQoaAZHQH9AAAAAAABoB030AWgIR0Bk9TAN5MURdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAZRiAPuogm3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQGUwyUkfLcN1fZQoaAZHQH9AAAAAAABoB030AWgIR0BlRP2GqPwNdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAZV4hJyyUtHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQGV2Oby6MBJ1ZS4="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 10000, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAgAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "2", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 10, "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", "__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 0x124f5c180>", "reset": "<function RolloutBuffer.reset at 0x124f5c220>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x124f5c2c0>", "add": "<function RolloutBuffer.add at 0x124f5c400>", "get": "<function RolloutBuffer.get at 0x124f5c4a0>", "_get_samples": "<function RolloutBuffer._get_samples at 0x124f5c540>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x124ee8b40>"}, "rollout_buffer_kwargs": {}, "normalize_advantage": false, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "macOS-15.7.4-x86_64-i386-64bit Darwin Kernel Version 24.6.0: Mon Jan 19 22:00:10 PST 2026; root:xnu-11417.140.69.708.3~1/RELEASE_X86_64", "Python": "3.11.11", "Stable-Baselines3": "2.4.1", "PyTorch": "2.2.2", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.1.2", "Gymnasium": "1.0.0"}}

results.json CHANGED Viewed

	@@ -1 +1 @@
1	- {"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-~~11T11~~:47:33.~~327138~~"}


1	+ {"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-11T12:01:16.222838"}