Initial commit

README.md

@@ -80,3 +80,8 @@ OrderedDict([('batch_size', 256),
              ('vf_coef', 0.489343896591493),
              ('normalize', False)])
 ```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

env_kwargs.yml

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

ppo-seals-CartPole-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6289bb697fc0f1e7637e587652d2d776145618358af91920d8992712a943879a
-size 139001
+oid sha256:f067bea7de65ea100f837bf04e9b0f55e433e70d6bd2aed071ac04bd9d9d39ff
+size 139005

ppo-seals-CartPole-v0/_stable_baselines3_version

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

ppo-seals-CartPole-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 0x7fc203108040>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc2031080d0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc203108160>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc2031081f0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7fc203108280>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7fc203108310>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc2031083a0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc203108430>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7fc2031084c0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc203108550>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc2031085e0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc203108670>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f4a59966ee0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f4a59966f70>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4a598ea040>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f4a598ea0d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f4a598ea160>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f4a598ea1f0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f4a598ea280>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f4a598ea310>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f4a598ea3a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f4a598ea430>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4a598ea4c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f4a598ea550>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7fc2030e5a80>"
+        "_abc_impl": "<_abc_data object at 0x7f4a59963d80>"
     },
     "verbose": 1,
     "policy_kwargs": {

ppo-seals-CartPole-v0/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:dfb42af0cb0886d40c42ccbae54457ef7c113e14260731dfef78f395def361e0
+size 52504

results.json

@@ -1 +1 @@
-{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-15T13:56:17.720409"}
+{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-18T09:56:38.670785"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:761f4110060ae02a1ee41e137ab087b607b678b3485f113639424090116ef535
+oid sha256:03f1d3442617ea155b2db3cfa07f3ddc9d43802819794da0b59f1af6f74b70b0
 size 6345