Initial commit

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,59 @@
+---
+library_name: stable-baselines3
+tags:
+- Swimmer-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 344.98 +/- 3.12
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Swimmer-v3
+      type: Swimmer-v3
+---
+
+# **SAC** Agent playing **Swimmer-v3**
+This is a trained model of a **SAC** agent playing **Swimmer-v3**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
+and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
+
+The RL Zoo is a training framework for Stable Baselines3
+reinforcement learning agents,
+with hyperparameter optimization and pre-trained agents included.
+
+## Usage (with SB3 RL Zoo)
+
+RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
+SB3: https://github.com/DLR-RM/stable-baselines3<br/>
+SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
+
+```
+# Download model and save it into the logs/ folder
+python -m utils.load_from_hub --algo sac --env Swimmer-v3 -orga sb3 -f logs/
+python enjoy.py --algo sac --env Swimmer-v3  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo sac --env Swimmer-v3 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo sac --env Swimmer-v3 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('gamma', 0.9999),
+             ('learning_starts', 10000),
+             ('n_timesteps', 1000000.0),
+             ('policy', 'MlpPolicy'),
+             ('use_sde', False),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,65 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - sac
+  - - env
+    - Swimmer-v3
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 20
+  - - eval_freq
+    - 10000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - use_sde: false
+  - - log_folder
+    - logs/
+  - - log_interval
+    - 10
+  - - n_eval_envs
+    - 5
+  - - n_evaluations
+    - 20
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - 1000000
+  - - n_trials
+    - 10
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - 2
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 594371
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - true
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,11 @@
+!!python/object/apply:collections.OrderedDict
+- - - gamma
+    - 0.9999
+  - - learning_starts
+    - 10000
+  - - n_timesteps
+    - 1000000.0
+  - - policy
+    - MlpPolicy
+  - - use_sde
+    - false

env_kwargs.yml

@@ -0,0 +1 @@
+{}

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9c6ea7416857de8a28018e1d1e59806fcfb5272319868b66abe4e31f63c1ad8
+size 1446986

results.json

@@ -0,0 +1 @@
+{"mean_reward": 344.9831635, "std_reward": 3.124083818786988, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T18:48:52.794420"}

sac-Swimmer-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92e916fb0f407fe6439f6ccc6a5aabaa127fb73fc860f5aba50e82ea893e0114
+size 3077195

sac-Swimmer-v3/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.1a8

sac-Swimmer-v3/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cf4d7ee1d9eea4534fc3dc4e8f355b883be8253573bad098c55679f7667f3f0
+size 557365

sac-Swimmer-v3/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9366140743ab0255f4236a6aa16e207bf0b9ee3ccc3bcc4cd71d28a0df3c47b5
+size 1108381

sac-Swimmer-v3/data

@@ -0,0 +1,113 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMCVNBQ1BvbGljeZSTlC4=",
+        "__module__": "stable_baselines3.sac.policies",
+        "__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 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()`` 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 0x7fa4e9fe2710>",
+        "_build": "<function SACPolicy._build at 0x7fa4e9fe27a0>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7fa4e9fe2830>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7fa4e9fe28c0>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7fa4e9fe2950>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7fa4e9fe29e0>",
+        "forward": "<function SACPolicy.forward at 0x7fa4e9fe2a70>",
+        "_predict": "<function SACPolicy._predict at 0x7fa4e9fe2b00>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7fa4e9fe2b90>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fa4e9fc5ab0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "use_sde": false
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float64",
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False]",
+        "_np_random": null,
+        "_shape": [
+            8
+        ]
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gASVFwwAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMA2xvd5SMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlGgGjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwKFlGgKiUMIAACAvwAAgL+UdJRijARoaWdolGgQaBJLAIWUaBSHlFKUKEsBSwKFlGgKiUMIAACAPwAAgD+UdJRijA1ib3VuZGVkX2JlbG93lGgQaBJLAIWUaBSHlFKUKEsBSwKFlGgHjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiiUMCAQGUdJRijA1ib3VuZGVkX2Fib3ZllGgQaBJLAIWUaBSHlFKUKEsBSwKFlGgoiUMCAQGUdJRijApfbnBfcmFuZG9tlIwUbnVtcHkucmFuZG9tLl9waWNrbGWUjBJfX3JhbmRvbXN0YXRlX2N0b3KUk5SMB01UMTk5MzeUhZRSlH2UKIwNYml0X2dlbmVyYXRvcpRoOIwFc3RhdGWUfZQojANrZXmUaBBoEksAhZRoFIeUUpQoSwFNcAKFlGgHjAJ1NJSJiIeUUpQoSwNoC05OTkr/////Sv////9LAHSUYolCwAkAAAAAAIBTwrOchwO1k3Lsq1vo5rLyz7aB2tUG72GhMU2ga7XM2RPmGJ90nHkvyKUbgMR5AUmeD0PkXeAYk5ITVczUSilk0giVvjTQnkRyegPwrb8Kc5t7PulgsQbadQNFC2591hZq6wQ0ZoO38/WlL2nvQmNDtVz3wndSzEZENy0IiW7Qjq53+xi2gE97nvlPMuwS2LmOXoWpGcquPXYtZytCgJ7F7scf9SIBXUvPJA/MGVJkRFeYcJ0K9RIXtela3jvE/0HPOrFftofdM9hYiaqizX97P8mUt2wPQx8xmX0bYJCrtwcdGUzeyPuOugD1z6ka3iX+IAalFvzQduPBTvXKQ9MBWnnfUFetzaqYhTrP0WHhMA/Ht9nWRUX4vUiuWi77gKSTLtizn2cHsqRyJMj43mOVvrbJtm3T5laAgDosou93H+ZNC0HiTVqmVP8Lsv3/JsoIWfaq43/tiUiTGgfVTTF1psbquA6tH5Icya9TC+0oH7X0htvTuZKBVDKM0C+fIAM8l/emTHKVm2ft/85WlYRpZ+XoFwvDLSCusSBQr4f7w/xdYy4GCKdeDDOfezLj5k6WvjminpO26pfQqfP9LJIYOUEgrwmoo5vMHp8a36i8kcQzwqUvi94rCQuS64xYFp7HcUF1aySvLmqGyXEyCeTa2GHwNpeYB9u4jyPRKocxbWSV4hOL16R9fH95KLmFfUaMD8zrZmLG5rLUfzMf1WOxNFwZpzInS+HWE1F4MWg2xcVst8upoi9ssNCNjtPbz1ley6m8DG7YZVNupay35yQ8/PAfu8uKRQsL7B4ArDFquqb66ABeDLPvviZ4c6y9Bi67Xye+uu6eNlYO/Boq5iiETBR9Kemi0T1eFf33JRNzywY9CJ1N9eTOb+3wxY/yK3iXhVISAMufwZby3YMCHwTAVr8o4ahkQaNipnYgwDvQT4XYuqBpmVAsUw41MjHfK43kXZ7UxPi/bB0FEr1H6UYynEiI2V3I7DDEsMFNEMyF3sA+J2YPBAGe9oh5woVr3lu3AeREERRPmD778jQMODrzkRfg4w7Zi1M+ozc9CW5Lim4SEBBFW6Q0ZKHiBgOBwE8pmXhOE1/4b4TsSX1+ZYlw/f1KJ/Doyf4YSKwzVGEdjTldkdS/lbivyQPaNIsxj4ggvb4u1CtbuK3vLbz6wSJwugR9g6TL1kkXqXR9H6xcRrB/5EQf0u+1EnjLN/GvsqKw2mvVrG/Vp7kINdL5dPO44b8Emce+3xqudjVdYf1J2QI56iTowjwYEK2NMLEnklukjknSLQDrqYlpFb0sx8/oKKXf9xVFD243YpO1XejusnBjhcKePsMmaqtTCh8MOXsSTQ+g3vDQeHxgc7LyqE/DtXwAt2Nmft5i2MJAiV1C8dszUjvdG0ItC9AYUxdQInTbakZGpO9lfldZKLOpuBfpMmYjosMX3Bylh5qUHtwPB6V+p2nMdGbKNFshf1v7Di6P/9oNGA/ZKCI4Cr8P/3/RJuAr8TQVDJyWE1UCRsrBeEDEoZzOm8mjDSYUVQC3/l9PkoCyZBMC3ynQWysYwNN+ThHNmCplKb6KFVFLfvVPHe3CkYDWCij8Ah8mHyyUkLeGRHU4YI3ssA8YLBsz2seUpJTi66EmJ9/X3qH2rWQ8yV3r3z0x8otWS8KXuh8JG6s9Rbjpx4koT3nWxAPW/xwrQcrUma4FMJcB6UJQIgU0saTe0xc1Wa64UXejfFvhXhPUgBgh8F3IRUeEghk4T8kRjv11pDDyeNgS1DpjBnqQ0IFh+uOrY6CUhNxF3AOYg0vjaujoedtaAtlDwJ78SI9UG1YfCG8ZQcrUU043NHNeBPXMoSD5YCKB64rhBUjF0hMzhi9TJi+lAm4l37EYPWejsFggpd1XhoOWxGdZIyZL7NPJO8LT5OAEwI2ky90KGNoH9dOsxWybS+A+YJizCfTrsxNhZ+bmgKqqY1yKqhF8UvY7abEVPVUxwoOvEcF0FSFIblSYB6vHzooATK1uwJufo46PxjTZXBXKfNd3RYl8uKh4YxkhIzV6d5Z9NzWZDoKl0PEmpSZTzr8qwEvcFvRLY0CoXKwUlkrEPAt6PzHP7EfwjEQfOWSKI0f7YgirTrrcUDCLrCDp2ByvIOpD6U0PCfz3yfKWtxhKGKAOu2sUE17MrHdmOmQ8Kc9R5AHiElStgJQnLkLLK0L/HVSwHIp7P9pI0RaeVafNh0l/Y+govRh+ZpHcqlfOL1rHcEc+CTVx2aB1WSp68UnQNR1MEVCP+aFoqpxpPSsokuDL/XUCFZbidfv6QB2BHRvWICx4jRNswO2iEG6qpRl+ox9Qqx0jy/Zp5R3T4io6M8EV7tNlELs5RiZ/vz1JFOnD2Cy3i3PHu0tqnwmcW3aR4qGp3e8GCqm+WzG/HQNw8L5uj+oiV0qICfkPtM+N5YvMnWCamTWZUo7JY6/9nOVFN97zISwyxFyB0/Fs67EuOU7CjW4WH02Meg7P/FucjrYjj1nNPn0ZQI20AvvhSqOVGjJdnkQsSOFOf4Xl9h8SRjZOdKyAo7hbBv/EPjVLiYEvstxTIXvrJtXtjHQvpXZAahJ/KEcWoxAmz+Fos89bXyZYlv9QOX3Rk31MTNx1e9myYJ6rMJqALpgMend+in7mcBBKdP8HK3aPvP7pyeX9pmHqgqznGsQya7OksVtc1Wh/2E2ZfkTQNDYzy4Gqp5b3mnrPzJKc7FREA7byhhaxtXJ5ho2VYtms60gxkNGONt5xJLAwuWsGHDiZlWG3gOA5DEjX4/uw8dksx/z1T7ly1/WsPSvUBeDJePM7Eq8LFYyGvPoCHX37NqX9sAinD7RXs+rzk9FA7hR5JyYzA4NHyNw58gu4yajvFeF6Zj8mq06dySURoZqkx4aWSJ5+9CTH0vkRa8ufqy0jjNE/illfH2I7PXsgomYo5UeAIgA6KF5vRvCSM2Qi2V9g7cvN4ss+4EM0sWDu1C7k09bLbxricGwT+CzIS15G8XYQJgUg4mDTp3NzvshbDuj7PVDkA/EuD26/IWeJhY24nKTut+UsKZhyDWA3rnsJZ9/xh8+vS6Qo5qZyj3hfWcV3KujEeJCVFdo/3UM6oy54jWkJqzJFC3SO1tbDF0RXLM/cbNRlcFaprTFcLPB7b1zGDZqLAq64ABV9oIT8+3VwlerzC+WIXzWwwM8xujB3367Ja4TGr977ZbfBZ5XeFWh+iITJKMGsk9ZUlb375ShwlsLSmk3Dma0eS2RmpSTqRW1SBVDgKPi52P9uW5nNypaMi84Ik7nYz7FxBjzTwSLxP+XDBL1OC67NDd7QpHuGm2A1xfX9eEK8C5R0lGKMA3Bvc5RNcAJ1jAloYXNfZ2F1c3OUSwCMBWdhdXNzlEcAAAAAAAAAAHVijAZfc2hhcGWUSwKFlHViLg==",
+        "dtype": "float32",
+        "low": "[-1. -1.]",
+        "high": "[1. 1.]",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_np_random": "RandomState(MT19937)",
+        "_shape": [
+            2
+        ]
+    },
+    "n_envs": 1,
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1635497676.6654458,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQGUdJRiLg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVygAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLCIaUaAOMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUNA5Kyzdt7tnT/4Y4luaCviv4d/orf+ReA/ulq82qqK2D9VNPifwq8AwCU827pC9QJASl3H1tGiA8DM+qqtugkEwJR0lGIu"
+    },
+    "_episode_num": 1000,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 990000,
+    "buffer_size": 1,
+    "batch_size": 256,
+    "learning_starts": 10000,
+    "tau": 0.005,
+    "gamma": 0.9999,
+    "gradient_steps": 1,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
+        "__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:\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    :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 0x7fa4ea444b90>",
+        "add": "<function ReplayBuffer.add at 0x7fa4ea444c20>",
+        "sample": "<function ReplayBuffer.sample at 0x7fa4e9fab7a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fa4e9fab830>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fa4ea49b5d0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gASVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -2.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "remove_time_limit_termination": false
+}

sac-Swimmer-v3/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68e86a5ec8016f3d9b2c3574fe5f77462542a90d28ad8135d96fbc512c4d136c
+size 1255

sac-Swimmer-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04dcfa180036146a386fb2353bfe45adc66f47813e900d4db0729dac9b2f2f1f
+size 1389317

sac-Swimmer-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:545b5b50ec960405adbfb760dfe430aaf2393f86521a07f99dfef85785c86ffd
+size 747

sac-Swimmer-v3/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.13.0-44-generic-x86_64-with-debian-bullseye-sid #49~20.04.1-Ubuntu SMP Wed May 18 18:44:28 UTC 2022
+Python: 3.7.10
+Stable-Baselines3: 1.5.1a8
+PyTorch: 1.11.0
+GPU Enabled: True
+Numpy: 1.21.2
+Gym: 0.21.0

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f28eb114243f50b05d47c21c50b4b1deca89c68f9ae85a3dcc25d332af20d03
+size 62602