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 +1,67 @@
+---
+library_name: stable-baselines3
+tags:
+- MountainCarContinuous-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 94.53 +/- 1.26
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: MountainCarContinuous-v0
+      type: MountainCarContinuous-v0
+---
+
+# **SAC** Agent playing **MountainCarContinuous-v0**
+This is a trained model of a **SAC** agent playing **MountainCarContinuous-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 sac --env MountainCarContinuous-v0 -orga sb3 -f logs/
+python enjoy.py --algo sac --env MountainCarContinuous-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo sac --env MountainCarContinuous-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo sac --env MountainCarContinuous-v0 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 512),
+             ('buffer_size', 50000),
+             ('ent_coef', 0.1),
+             ('gamma', 0.9999),
+             ('gradient_steps', 32),
+             ('learning_rate', 0.0003),
+             ('learning_starts', 0),
+             ('n_timesteps', 50000.0),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(log_std_init=-3.67, net_arch=[64, 64])'),
+             ('tau', 0.01),
+             ('train_freq', 32),
+             ('use_sde', True),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,59 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - sac
+  - - env
+    - MountainCarContinuous-v0
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 10
+  - - eval_freq
+    - 10000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - rl-trained-agents/
+  - - log_interval
+    - -1
+  - - n_evaluations
+    - 20
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 10
+  - - num_threads
+    - -1
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 765152961
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - true
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,27 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 512
+  - - buffer_size
+    - 50000
+  - - ent_coef
+    - 0.1
+  - - gamma
+    - 0.9999
+  - - gradient_steps
+    - 32
+  - - learning_rate
+    - 0.0003
+  - - learning_starts
+    - 0
+  - - n_timesteps
+    - 50000.0
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(log_std_init=-3.67, net_arch=[64, 64])
+  - - tau
+    - 0.01
+  - - train_freq
+    - 32
+  - - use_sde
+    - true

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0f9af8fa44af30ada7bf383eeaaeb7227602c8a983b47328b325b1e68efb42d
+size 255496

results.json

@@ -0,0 +1 @@
+{"mean_reward": 94.53228179999999, "std_reward": 1.2560546082455812, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T19:08:05.668186"}

sac-MountainCarContinuous-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ab1fc5997732993f0a699593d76824913cd9d9b1072a2f05a0d288acace494d
+size 237969

sac-MountainCarContinuous-v0/_stable_baselines3_version

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

sac-MountainCarContinuous-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95ad99652a36250bac834055334a300020e82d1d2b8bc6381f1519c0795f49c8
+size 39675

sac-MountainCarContinuous-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9f5275ad197ccf83134818f0f3a3fb9ec9f8f3121afa27845c06127fd62176c
+size 78109

sac-MountainCarContinuous-v0/data

@@ -0,0 +1,124 @@
+{
+    "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 0x7fd3ac686710>",
+        "_build": "<function SACPolicy._build at 0x7fd3ac6867a0>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7fd3ac686830>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7fd3ac6868c0>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7fd3ac686950>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7fd3ac6869e0>",
+        "forward": "<function SACPolicy.forward at 0x7fd3ac686a70>",
+        "_predict": "<function SACPolicy._predict at 0x7fd3ac686b00>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7fd3ac686b90>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fd3ac669ab0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "log_std_init": -3.67,
+        "net_arch": [
+            64,
+            64
+        ],
+        "use_sde": true
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "low": "[-1.2  -0.07]",
+        "high": "[0.6  0.07]",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_np_random": null,
+        "_shape": [
+            2
+        ]
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gASVCwwAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMA2xvd5SMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlGgGjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgKiUMEAACAv5R0lGKMBGhpZ2iUaBBoEksAhZRoFIeUUpQoSwFLAYWUaAqJQwQAAIA/lHSUYowNYm91bmRlZF9iZWxvd5RoEGgSSwCFlGgUh5RSlChLAUsBhZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQGUdJRijA1ib3VuZGVkX2Fib3ZllGgQaBJLAIWUaBSHlFKUKEsBSwGFlGgoiWgrdJRijApfbnBfcmFuZG9tlIwUbnVtcHkucmFuZG9tLl9waWNrbGWUjBJfX3JhbmRvbXN0YXRlX2N0b3KUk5SMB01UMTk5MzeUhZRSlH2UKIwNYml0X2dlbmVyYXRvcpRoN4wFc3RhdGWUfZQojANrZXmUaBBoEksAhZRoFIeUUpQoSwFNcAKFlGgHjAJ1NJSJiIeUUpQoSwNoC05OTkr/////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+XDBL1OC67NDd7QpHuGm2A1xfX9eEK8C5R0lGKMA3Bvc5RNcAJ1jAloYXNfZ2F1c3OUSwCMBWdhdXNzlEcAAAAAAAAAAHVijAZfc2hhcGWUSwGFlHViLg==",
+        "dtype": "float32",
+        "low": "[-1.]",
+        "high": "[1.]",
+        "bounded_below": "[ True]",
+        "bounded_above": "[ True]",
+        "_np_random": "RandomState(MT19937)",
+        "_shape": [
+            1
+        ]
+    },
+    "n_envs": 1,
+    "num_timesteps": 50016,
+    "_total_timesteps": 50000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1614621345.1958349,
+    "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": null,
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVkgAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLAoaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUMIXDUBv1EsdLyUdJRiLg=="
+    },
+    "_episode_num": 342,
+    "use_sde": true,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.000320000000000098,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 50016,
+    "buffer_size": 1,
+    "batch_size": 512,
+    "learning_starts": 0,
+    "tau": 0.01,
+    "gamma": 0.9999,
+    "gradient_steps": 32,
+    "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 0x7fd3acae8b90>",
+        "add": "<function ReplayBuffer.add at 0x7fd3acae8c20>",
+        "sample": "<function ReplayBuffer.sample at 0x7fd3ac64f7a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fd3ac64f830>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fd3acb3f5d0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gASVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLIGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -1.0,
+    "log_ent_coef": null,
+    "ent_coef": 0.1,
+    "target_update_interval": 1,
+    "ent_coef_optimizer": null,
+    "_last_dones": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQCUdJRiLg=="
+    },
+    "remove_time_limit_termination": false
+}

sac-MountainCarContinuous-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0b88f7bbe7a13b1b4f829bade20333b5fee02eacaf758a448b986bc0c682736
+size 100168

sac-MountainCarContinuous-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39440af5158e3fb47ecc525e9d329ecbd7c856bf70fd565c749cc2c45263e188
+size 747

sac-MountainCarContinuous-v0/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 sha256:6cc721f2a3667bb5edbd1f98be2acb2ff9b0f7b0195d4166f0511219e1a1fe5a
+size 10559