Initial commit

README.md

@@ -76,3 +76,8 @@ OrderedDict([('clip_range', 0.2),
              ('use_sde', True),
              ('normalize', False)])
 ```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

env_kwargs.yml

@@ -1 +1 @@
-{}
+render_mode: rgb_array

ppo-Pendulum-v1.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa88fec6c8ad62de18627fac90373e1cb1f7005da2df367889e90b851c66aa1c
-size 137828
+oid sha256:c7f24b097f622e1f05f5302b9a218395628990366719ec506b9a7cb821f97659
+size 137832

ppo-Pendulum-v1/_stable_baselines3_version

@@ -1 +1 @@
-2.1.0
+2.2.0a3

ppo-Pendulum-v1/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 0x7fd294b67040>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd294b670d0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd294b67160>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd294b671f0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7fd294b67280>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7fd294b67310>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd294b673a0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd294b67430>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7fd294b674c0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd294b67550>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd294b675e0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd294b67670>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fbe4d5bbee0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fbe4d5bbf70>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fbe4d540040>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fbe4d5400d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fbe4d540160>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fbe4d5401f0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fbe4d540280>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fbe4d540310>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fbe4d5403a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fbe4d540430>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fbe4d5404c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fbe4d540550>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7fd294b42ab0>"
+        "_abc_impl": "<_abc_data object at 0x7fbe4d5b8cf0>"
     },
     "verbose": 1,
     "policy_kwargs": {},

ppo-Pendulum-v1/system_info.txt

@@ -1,6 +1,6 @@
 - OS: Linux-5.4.0-156-generic-x86_64-with-glibc2.29 # 173-Ubuntu SMP Tue Jul 11 07:25:22 UTC 2023
 - Python: 3.8.10
-- Stable-Baselines3: 2.1.0
+- Stable-Baselines3: 2.2.0a3
 - PyTorch: 2.0.1+cu117
 - GPU Enabled: False
 - Numpy: 1.24.4

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc4ccb77c13e09f524899e42ab016875f30055b24e76e4f43eca6047088e5f14
+size 174142

results.json

@@ -1 +1 @@
-{"mean_reward": -189.2534682, "std_reward": 66.36133815611241, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-15T13:52:49.960932"}
+{"mean_reward": -189.2534682, "std_reward": 66.36133815611241, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-18T09:50:19.957740"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5ce2124af89a6fc975e8699dd5cfc9103572037576aa9591d9f0cb6038a2d22
+oid sha256:690af8420de0d7622537e219353fd187a2691b8cf017e74df2f93166a8b7d477
 size 15240