Initial Commit

ppo-seals/Walker2d-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:134b08e1ff9a8492abef485e4a8d9be53da3bfbcb3d81f797f5280ee98d2bb90
+oid sha256:34dbeb60f28081021872492e1a8eeb843f0376d4fde2ee7bf88d612a916b41b8
 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 0x7fd03d774f70>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd03d777040>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd03d7770d0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd03d777160>",
-        "_build": "<function ActorCriticPolicy._build at 0x7fd03d7771f0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7fd03d777280>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd03d777310>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7fd03d7773a0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd03d777430>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd03d7774c0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd03d777550>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f2441969f70>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f244196d040>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f244196d0d0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f244196d160>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f244196d1f0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f244196d280>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f244196d310>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f244196d3a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f244196d430>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f244196d4c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f244196d550>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7fd03d76f6c0>"
+        "_abc_impl": "<_abc_data object at 0x7f24419646c0>"
     },
     "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": "2022-05-27T12:11:24.490550"}
+{"mean_reward": 1429.1260997000002, "std_reward": 411.7513179252928, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-30T12:08:39.184939"}