Initial commit

README.md

@@ -77,3 +77,8 @@ OrderedDict([('batch_size', 128),
              ('train_freq', 256),
              ('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:ae31f2f40c11cde1dbcfdd79b2b17ca41521be424e26584eb281317f745a1d16
+size 435245

results.json

@@ -1 +1 @@
-{"mean_reward": 28.9023299, "std_reward": 1.6711585563886182, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-15T13:55:41.749317"}
+{"mean_reward": 28.9023299, "std_reward": 1.6711585563886182, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-18T09:55:50.831805"}

sac-seals-Swimmer-v1.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c995510e331e9b3b1660f1e4df2df5e89512b21af0c698b852460bceb9d07e6
-size 5580789
+oid sha256:8a1f4409a2d8c327f0b51913d10353beadf6d5f856451d53c43eeb26c67fb8e1
+size 5580793

sac-seals-Swimmer-v1/_stable_baselines3_version

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

sac-seals-Swimmer-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 0x7f739ad838b0>",
-        "_build": "<function SACPolicy._build at 0x7f739ad83940>",
-        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7f739ad839d0>",
-        "reset_noise": "<function SACPolicy.reset_noise at 0x7f739ad83a60>",
-        "make_actor": "<function SACPolicy.make_actor at 0x7f739ad83af0>",
-        "make_critic": "<function SACPolicy.make_critic at 0x7f739ad83b80>",
-        "forward": "<function SACPolicy.forward at 0x7f739ad83c10>",
-        "_predict": "<function SACPolicy._predict at 0x7f739ad83ca0>",
-        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7f739ad83d30>",
+        "__init__": "<function SACPolicy.__init__ at 0x7f530a866700>",
+        "_build": "<function SACPolicy._build at 0x7f530a866790>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7f530a866820>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7f530a8668b0>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7f530a866940>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7f530a8669d0>",
+        "forward": "<function SACPolicy.forward at 0x7f530a866a60>",
+        "_predict": "<function SACPolicy._predict at 0x7f530a866af0>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7f530a866b80>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f739ad84870>"
+        "_abc_impl": "<_abc_data object at 0x7f530a85cb70>"
     },
     "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 0x7f739ad4d820>",
-        "add": "<function ReplayBuffer.add at 0x7f739ad4d8b0>",
-        "sample": "<function ReplayBuffer.sample at 0x7f739ad4d940>",
-        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f739ad4d9d0>",
-        "_maybe_cast_dtype": "<staticmethod object at 0x7f739ad53580>",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7f530a8b3700>",
+        "add": "<function ReplayBuffer.add at 0x7f530a8b3790>",
+        "sample": "<function ReplayBuffer.sample at 0x7f530a8b3820>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f530a8b38b0>",
+        "_maybe_cast_dtype": "<staticmethod object at 0x7f530a8ad880>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f739ad535a0>"
+        "_abc_impl": "<_abc_data object at 0x7f530a8ad8a0>"
     },
     "replay_buffer_kwargs": {},
     "train_freq": {

sac-seals-Swimmer-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 sha256:2fd65d60136370c24d24b1bbdd4d9b6ea00503f6a2dc4bb79758537234f8795e
+oid sha256:bc0381fc9e16ccda3dd2904756e8ac0b4ebe97bff618441d0315930299befcad
 size 27986