Initial commit

ppo-MountainCar-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3c4eced22a46d9fa9e932e2d940a07e58fd4d6ee73166cdbf6bbf1bb988bae5
+oid sha256:fe6c0fc4eb1b91ee39beb0e6ce15897b7640aa6ee1f598db347853080c297726
 size 141785

ppo-MountainCar-v0/data

@@ -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 0x78b86ec6d1b0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78b86ec6d240>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78b86ec6d2d0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78b86ec6d360>",
-        "_build": "<function ActorCriticPolicy._build at 0x78b86ec6d3f0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x78b86ec6d480>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x78b86ec6d510>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78b86ec6d5a0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x78b86ec6d630>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78b86ec6d6c0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78b86ec6d750>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x78b86ec6d7e0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7ca2517911b0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ca251791240>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ca2517912d0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ca251791360>",
+        "_build": "<function ActorCriticPolicy._build at 0x7ca2517913f0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7ca251791480>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ca251791510>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ca2517915a0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7ca251791630>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ca2517916c0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ca251791750>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ca2517917e0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x78b86ec5b680>"
+        "_abc_impl": "<_abc._abc_data object at 0x7ca25177f580>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -92,14 +92,14 @@
         "__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 0x78b86edcfd90>",
-        "reset": "<function RolloutBuffer.reset at 0x78b86edcfe20>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x78b86edcfeb0>",
-        "add": "<function RolloutBuffer.add at 0x78b86edcff40>",
-        "get": "<function RolloutBuffer.get at 0x78b86edd8040>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x78b86edd80d0>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x7ca2516ebd90>",
+        "reset": "<function RolloutBuffer.reset at 0x7ca2516ebe20>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7ca2516ebeb0>",
+        "add": "<function RolloutBuffer.add at 0x7ca2516ebf40>",
+        "get": "<function RolloutBuffer.get at 0x7ca2516fc040>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x7ca2516fc0d0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x78b86ed84b40>"
+        "_abc_impl": "<_abc._abc_data object at 0x7ca2516aff00>"
     },
     "rollout_buffer_kwargs": {},
     "batch_size": 64,

results.json

@@ -1 +1 @@
-{"mean_reward": -96.4, "std_reward": 7.787168933572714, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-12-11T18:27:19.569290"}
+{"mean_reward": -96.4, "std_reward": 7.787168933572714, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-12-11T19:25:35.814154"}