Initial commit

.gitattributes

@@ -29,3 +29,4 @@ 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 +1,70 @@
+---
+library_name: stable-baselines3
+tags:
+- seals/Swimmer-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 367.88 +/- 1.43
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: seals/Swimmer-v0
+      type: seals/Swimmer-v0
+---
+
+# **PPO** Agent playing **seals/Swimmer-v0**
+This is a trained model of a **PPO** agent playing **seals/Swimmer-v0**
+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 ppo --env seals/Swimmer-v0 -orga HumanCompatibleAI -f logs/
+python enjoy.py --algo ppo --env seals/Swimmer-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo ppo --env seals/Swimmer-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo ppo --env seals/Swimmer-v0 -f logs/ -orga HumanCompatibleAI
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 8),
+             ('clip_range', 0.1),
+             ('ent_coef', 5.167107294612664e-08),
+             ('gae_lambda', 0.95),
+             ('gamma', 0.999),
+             ('learning_rate', 0.0001214437022727675),
+             ('max_grad_norm', 2),
+             ('n_epochs', 20),
+             ('n_steps', 2048),
+             ('n_timesteps', 1000000.0),
+             ('normalize', True),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs',
+              'dict(activation_fn=nn.Tanh, net_arch=[dict(pi=[64, 64], vf=[64, '
+              '64])])'),
+             ('vf_coef', 0.6162112311062333),
+             ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
+```

args.yml

@@ -0,0 +1,75 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - device
+    - cpu
+  - - env
+    - seals/Swimmer-v0
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - - seals
+  - - hyperparams
+    - null
+  - - log_folder
+    - seals_experts_wandb/
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 1
+  - - n_evaluations
+    - null
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 500
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - 1
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 9
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/seals/Swimmer-v0__ppo__9__1658503223
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - seals-experts

config.yml

@@ -0,0 +1,29 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 8
+  - - clip_range
+    - 0.1
+  - - ent_coef
+    - 5.167107294612664e-08
+  - - gae_lambda
+    - 0.95
+  - - gamma
+    - 0.999
+  - - learning_rate
+    - 0.0001214437022727675
+  - - max_grad_norm
+    - 2
+  - - n_epochs
+    - 20
+  - - n_steps
+    - 2048
+  - - n_timesteps
+    - 1000000.0
+  - - normalize
+    - true
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(activation_fn=nn.Tanh, net_arch=[dict(pi=[64, 64], vf=[64, 64])])
+  - - vf_coef
+    - 0.6162112311062333

env_kwargs.yml

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

ppo-seals-Swimmer-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3143cb0982c56eb56b7ab75b95cdb121ec73f50a06d7bcf55647f41da5bac555
+size 154313

ppo-seals-Swimmer-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.6.0

ppo-seals-Swimmer-v0/data

@@ -0,0 +1,118 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":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 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()`` 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 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 0x7f9c471dc790>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9c471dc820>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9c471dc8b0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9c471dc940>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f9c471dc9d0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f9c471dca60>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9c471dcaf0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f9c471dcb80>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9c471dcc10>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9c471dcca0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9c471dcd30>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f9c471d3cc0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVaAAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARUYW5olJOUjAhuZXRfYXJjaJRdlH2UKIwCcGmUXZQoS0BLQGWMAnZmlF2UKEtAS0BldWF1Lg==",
+        "activation_fn": "<class 'torch.nn.modules.activation.Tanh'>",
+        "net_arch": [
+            {
+                "pi": [
+                    64,
+                    64
+                ],
+                "vf": [
+                    64,
+                    64
+                ]
+            }
+        ]
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float64",
+        "_shape": [
+            10
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWV6wsAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAAAAIC/AACAv5RoCksChZSMAUOUdJRSlIwEaGlnaJRoEiiWCAAAAAAAAAAAAIA/AACAP5RoCksChZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolgIAAAAAAAAAAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYCAAAAAAAAAAEBlGghSwKFlGgVdJRSlIwKX25wX3JhbmRvbZSMFG51bXB5LnJhbmRvbS5fcGlja2xllIwSX19yYW5kb21zdGF0ZV9jdG9ylJOUjAdNVDE5OTM3lIWUUpR9lCiMDWJpdF9nZW5lcmF0b3KUaDCMBXN0YXRllH2UKIwDa2V5lGgSKJbACQAAAAAAAAAAAIBTwrOchwO1k3Lsq1vo5rLyz7aB2tUG72GhMU2ga7XM2RPmGJ90nHkvyKUbgMR5AUmeD0PkXeAYk5ITVczUSilk0giVvjTQnkRyegPwrb8Kc5t7PulgsQbadQNFC2591hZq6wQ0ZoO38/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+XDBL1OC67NDd7QpHuGm2A1xfX9eEK8C5RoB4wCdTSUiYiHlFKUKEsDaAtOTk5K/////0r/////SwB0lGJNcAKFlGgVdJRSlIwDcG9zlE1wAnWMCWhhc19nYXVzc5RLAIwFZ2F1c3OURwAAAAAAAAAAdWJ1Yi4=",
+        "dtype": "float32",
+        "_shape": [
+            2
+        ],
+        "low": "[-1. -1.]",
+        "high": "[1. 1.]",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 1001472,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1658503227.9944735,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/seals/Swimmer-v0__ppo__9__1658503223/seals-Swimmer-v0",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVxQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZQAAAAAAAAAKgNxuOOlIa/WKSZ6peFpT/Y1R+KPhuSP1S6YsIfEKo/qokcJXwstz/ordGVTjGJvw58+bg8ErG/gLfoemkWgj8gPmAejk6Qv0CbIPSxZ4I/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwqGlIwBQ5R0lFKULg=="
+    },
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.0014719999999999178,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 9780,
+    "n_steps": 2048,
+    "gamma": 0.999,
+    "gae_lambda": 0.95,
+    "ent_coef": 5.167107294612664e-08,
+    "vf_coef": 0.6162112311062333,
+    "max_grad_norm": 2,
+    "batch_size": 8,
+    "n_epochs": 20,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

ppo-seals-Swimmer-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede79600cb9ec742bebbffb56990305e0eabcfcab34be9664199097219365907
+size 89264

ppo-seals-Swimmer-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d10d0a9876274b21b07fb180e71097dbd3c4b36ee0bfa70dce8a0d55f5eb162f
+size 43902

ppo-seals-Swimmer-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

ppo-seals-Swimmer-v0/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.4.0-122-generic-x86_64-with-glibc2.29 #138-Ubuntu SMP Wed Jun 22 15:00:31 UTC 2022
+Python: 3.8.10
+Stable-Baselines3: 1.6.0
+PyTorch: 1.11.0+cu102
+GPU Enabled: False
+Numpy: 1.22.3
+Gym: 0.21.0

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a9c9f0a679f0427696f0a6e1af3ee15a2e1d957f943e57a2f0547eb8417ce3c
+size 1403007

results.json

@@ -0,0 +1 @@
+{"mean_reward": 367.8820217, "std_reward": 1.4284948440936103, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-25T13:03:34.786779"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1c71d991ae619fb693f64faf20e0d3d7585bff382157ed4fc992e824bf44450
+size 33502

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303c1dc25c22f3721a3946ee16ca84d34068cfc5193616634dd8ae1434b01e22
+size 4394