Initial Commit

ppo-seals/Walker2d-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47e23c3bc10534741c1cea0a566a4c82bc6cc75f39a34f602cf9da83336aafc9
+oid sha256:02a03297205793095695539c4b319fcf8499c2c880ef9f9e1a2b1e48a059c8f3
 size 1750082

ppo-seals/Walker2d-v0/data

@@ -4,19 +4,19 @@
         ":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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7f45c4d34f70>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f45c4d38040>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f45c4d380d0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f45c4d38160>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f45c4d381f0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f45c4d38280>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f45c4d38310>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f45c4d383a0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f45c4d38430>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f45c4d384c0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f45c4d38550>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7faf6e34ef70>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7faf6e353040>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7faf6e3530d0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7faf6e353160>",
+        "_build": "<function ActorCriticPolicy._build at 0x7faf6e3531f0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7faf6e353280>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7faf6e353310>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7faf6e3533a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7faf6e353430>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7faf6e3534c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7faf6e353550>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f45c4d2f6c0>"
+        "_abc_impl": "<_abc_data object at 0x7faf6e349840>"
     },
     "verbose": 1,
     "policy_kwargs": {

results.json

@@ -1 +1 @@
-{"mean_reward": 1429.1260997000002, "std_reward": 411.7513179252928, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-30T12:53:42.750829"}
+{"mean_reward": 1429.1260997000002, "std_reward": 411.7513179252928, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-30T14:02:59.995868"}