My trained model

PPO_model_v1.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9ef3df4a3722a1888b529f7bf7fe1e3e6a39ea38a83914b6df6bdaa7e9a813b
+oid sha256:cd91aa79bcb019d0531a3a90fb40c0af7e6d12755a90c30d5fbcaa9a805e70e0
 size 29447806

PPO_model_v1/data

@@ -4,9 +4,9 @@
         ":serialized:": "gAWVPgAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMFEFjdG9yQ3JpdGljQ25uUG9saWN5lJOULg==",
         "__module__": "stable_baselines3.common.policies",
         "__doc__": "\n    CNN 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 ActorCriticCnnPolicy.__init__ at 0x337ecb380>",
+        "__init__": "<function ActorCriticCnnPolicy.__init__ at 0x3326c7380>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x337eb7a40>"
+        "_abc_impl": "<_abc._abc_data object at 0x3326bb700>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -97,14 +97,14 @@
         "__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 0x337e02b60>",
-        "reset": "<function RolloutBuffer.reset at 0x337e02c00>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x337e02ca0>",
-        "add": "<function RolloutBuffer.add at 0x337e02de0>",
-        "get": "<function RolloutBuffer.get at 0x337e02e80>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x337e02f20>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x332606b60>",
+        "reset": "<function RolloutBuffer.reset at 0x332606c00>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x332606ca0>",
+        "add": "<function RolloutBuffer.add at 0x332606de0>",
+        "get": "<function RolloutBuffer.get at 0x332606e80>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x332606f20>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x337e0acc0>"
+        "_abc_impl": "<_abc._abc_data object at 0x332602a00>"
     },
     "rollout_buffer_kwargs": {},
     "batch_size": 128,

README.md

@@ -16,7 +16,7 @@ model-index:
       type: CarRacing-v2
     metrics:
     - type: mean_reward
-      value: 850.01 +/- 137.65
+      value: 883.30 +/- 66.01
       name: mean_reward
       verified: false
 ---

results.json

@@ -1 +1 @@
-{"mean_reward": 850.0146951, "std_reward": 137.65236984414358, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-19T13:37:19.028795"}
+{"mean_reward": 883.2959205999999, "std_reward": 66.01289818923838, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-19T14:56:12.002456"}