Initial commit

README.md

@@ -77,3 +77,8 @@ OrderedDict([('batch_size', 64),
              ('train_freq', 8),
              ('normalize', False)])
 ```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f16fc62f4df2c3b4e46eb0d72ed453b9aa68885aec90a9e9110ad145c7de0b20
+size 491501

results.json

@@ -1 +1 @@
-{"mean_reward": 367.4834745, "std_reward": 59.61112469905793, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-15T13:55:04.652816"}
+{"mean_reward": 367.4834745, "std_reward": 59.61112469905793, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-18T09:55:03.230088"}

sac-seals-Humanoid-v1.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:286748292454082f9a382da8c39c89006dd306fa217ed0143ce87a094df634c5
-size 12379151
+oid sha256:da6eda93cf34bab5eb9c8a123755a9e75548af5da816e8371132811f986ca328
+size 12379155

sac-seals-Humanoid-v1/_stable_baselines3_version

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

sac-seals-Humanoid-v1/data

@@ -5,17 +5,17 @@
         "__module__": "stable_baselines3.sac.policies",
         "__annotations__": "{'actor': <class 'stable_baselines3.sac.policies.Actor'>, 'critic': <class 'stable_baselines3.common.policies.ContinuousCritic'>, 'critic_target': <class 'stable_baselines3.common.policies.ContinuousCritic'>}",
         "__doc__": "\n    Policy class (with both actor and critic) for SAC.\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 use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\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    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ",
-        "__init__": "<function SACPolicy.__init__ at 0x7f13d0bf48b0>",
-        "_build": "<function SACPolicy._build at 0x7f13d0bf4940>",
-        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7f13d0bf49d0>",
-        "reset_noise": "<function SACPolicy.reset_noise at 0x7f13d0bf4a60>",
-        "make_actor": "<function SACPolicy.make_actor at 0x7f13d0bf4af0>",
-        "make_critic": "<function SACPolicy.make_critic at 0x7f13d0bf4b80>",
-        "forward": "<function SACPolicy.forward at 0x7f13d0bf4c10>",
-        "_predict": "<function SACPolicy._predict at 0x7f13d0bf4ca0>",
-        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7f13d0bf4d30>",
+        "__init__": "<function SACPolicy.__init__ at 0x7efec9bcc700>",
+        "_build": "<function SACPolicy._build at 0x7efec9bcc790>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7efec9bcc820>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7efec9bcc8b0>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7efec9bcc940>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7efec9bcc9d0>",
+        "forward": "<function SACPolicy.forward at 0x7efec9bcca60>",
+        "_predict": "<function SACPolicy._predict at 0x7efec9bccaf0>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7efec9bccb80>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f13d0bf5900>"
+        "_abc_impl": "<_abc_data object at 0x7efec9bc2b40>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -103,13 +103,13 @@
         ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
         "__module__": "stable_baselines3.common.buffers",
         "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\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 n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n        Cannot be used in combination with handle_timeout_termination.\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ",
-        "__init__": "<function ReplayBuffer.__init__ at 0x7f13d0bbf820>",
-        "add": "<function ReplayBuffer.add at 0x7f13d0bbf8b0>",
-        "sample": "<function ReplayBuffer.sample at 0x7f13d0bbf940>",
-        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f13d0bbf9d0>",
-        "_maybe_cast_dtype": "<staticmethod object at 0x7f13d0bc5610>",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7efec9c19700>",
+        "add": "<function ReplayBuffer.add at 0x7efec9c19790>",
+        "sample": "<function ReplayBuffer.sample at 0x7efec9c19820>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7efec9c198b0>",
+        "_maybe_cast_dtype": "<staticmethod object at 0x7efec9c13850>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f13d0bc5630>"
+        "_abc_impl": "<_abc_data object at 0x7efec9c13870>"
     },
     "replay_buffer_kwargs": {},
     "train_freq": {

sac-seals-Humanoid-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

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b3bc20573122fa398a763659bfb3306c833ba2ef0553f2a24a212b615b801e3
+oid sha256:1fc83703bd5eb53aba76bd7a079c25215141c36de58f9b1697f1bbf9d1fd5d33
 size 58659