Initial commit

.gitattributes

@@ -25,3 +25,5 @@ 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
+vec_normalize.pkl 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: 162.15 +/- 8.19
+      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 ernestumorga -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 ernestumorga
+```
+
+## 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
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - seals_experts
+  - - log_interval
+    - -1
+  - - 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
+    - 4
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 1907246581
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - total_n_trials
+    - null
+  - - track
+    - false
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - sb3

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 sha256:27719fc02dc4752374491aa8eaa7d9154bb5479fa7f174ce1681f3fbec0ce559
+size 151224

ppo-seals-Swimmer-v0/_stable_baselines3_version

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

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 0x7fe17094e670>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fe17094e700>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fe17094e790>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fe17094e820>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fe17094e8b0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fe17094e940>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fe17094e9d0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fe17094ea60>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fe17094eaf0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fe17094eb80>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fe17094ec10>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fe17094a240>"
+    },
+    "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": 1651240812.9806583,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "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:": "gAWVxQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZQAAAAAAAAADL8Rc+Sprc/aHsbnXtOlb8wYwdN2TelvzTI1aHxNZk/rXXAmfMJtr9Ii80N75elP34Gpqnqlrk/p5tiWM6fpb8gRb1WKr+rP/B+rDrj17e/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:ccfd306c8fd6da2ba0cf8a62fc7de1e4d2fd6c413e14f22ecf8954f8248a489b
+size 86167

ppo-seals-Swimmer-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc9f3f1501d5e00506989044800dc82ad16cf50db0b686ac21585a81f2b98256
+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-5.4.0-121-generic-x86_64-with-glibc2.29 #137-Ubuntu SMP Wed Jun 15 13:33:07 UTC 2022
+Python: 3.8.10
+Stable-Baselines3: 1.5.1a8
+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:ef141d5fe53027695469d669878810647ca84f509ab9c7f3d65c23ee559644fc
+size 1102283

results.json

@@ -0,0 +1 @@
+{"mean_reward": 162.1493199, "std_reward": 8.194538092541295, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-11T14:41:13.376367"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89cee82d6b9af4ab06bd80c9081085d0988e9084185656b75df49b2e1bdd9837
+size 32958

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e658385122ebcd96b9a4dfb52599173d9ac67882d291616288fddba98442215
+size 4394