Initial commit

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst 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 +1,79 @@
+---
+library_name: stable-baselines3
+tags:
+- MountainCarContinuous-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: MountainCarContinuous-v0
+      type: MountainCarContinuous-v0
+    metrics:
+    - type: mean_reward
+      value: 94.74 +/- 0.46
+      name: mean_reward
+      verified: false
+---
+
+# **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
+
+Install the RL Zoo (with SB3 and SB3-Contrib):
+```bash
+pip install rl_zoo3
+```
+
+```
+# Download model and save it into the logs/ folder
+python -m rl_zoo3.load_from_hub --algo sac --env MountainCarContinuous-v0 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo sac --env MountainCarContinuous-v0  -f logs/
+```
+
+If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
+```
+python -m rl_zoo3.load_from_hub --algo sac --env MountainCarContinuous-v0 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo sac --env MountainCarContinuous-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo sac --env MountainCarContinuous-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo sac --env MountainCarContinuous-v0 -f logs/ -orga qgallouedec
+```
+
+## 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 +1,79 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - sac
+  - - device
+    - auto
+  - - env
+    - MountainCarContinuous-v0
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 20
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 5
+  - - 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
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 1826025095
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/MountainCarContinuous-v0__sac__1826025095__1670943692
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - openrlbenchmark
+  - - wandb_project_name
+    - sb3
+  - - yaml_file
+    - null

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 sha256:8de3e74b9e59c0262f73b349cd70a767b9a42adad126c07556db716e92da072f
+size 253998

results.json

@@ -0,0 +1 @@
+{"mean_reward": 94.73531580000001, "std_reward": 0.4640893226590776, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T15:29:53.496950"}

sac-MountainCarContinuous-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd7b24d43eb2508446a4aa82402fb57b596edf0af635aee246b62cd0e4e13823
+size 243194

sac-MountainCarContinuous-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.8.0a6

sac-MountainCarContinuous-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd601fadd3189b0e033aa9f5616252d4cb274332cbe56b59ee57bfbb001a414f
+size 41702

sac-MountainCarContinuous-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:767553faed59f9eed394bab8037c539fcd44a9284b792882a406bcf277dca36e
+size 81337

sac-MountainCarContinuous-v0/data

@@ -0,0 +1,124 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMCVNBQ1BvbGljeZSTlC4=",
+        "__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 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 0x7f08a7f12ca0>",
+        "_build": "<function SACPolicy._build at 0x7f08a7f12d30>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7f08a7f12dc0>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7f08a7f12e50>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7f08a7f12ee0>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7f08a7f12f70>",
+        "forward": "<function SACPolicy.forward at 0x7f08a7f1a040>",
+        "_predict": "<function SACPolicy._predict at 0x7f08a7f1a0d0>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7f08a7f1a160>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f08a7f1c080>"
+    },
+    "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:": "gAWVYwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAACamZm/KVyPvZRoCksChZSMAUOUdJRSlIwEaGlnaJRoEiiWCAAAAAAAAACamRk/KVyPPZRoCksChZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolgIAAAAAAAAAAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYCAAAAAAAAAAEBlGghSwKFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu",
+        "dtype": "float32",
+        "_shape": [
+            2
+        ],
+        "low": "[-1.2  -0.07]",
+        "high": "[0.6  0.07]",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWVBAwAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAYWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBAAAAAAAAAAAAIC/lGgKSwGFlIwBQ5R0lFKUjARoaWdolGgSKJYEAAAAAAAAAAAAgD+UaApLAYWUaBV0lFKUjA1ib3VuZGVkX2JlbG93lGgSKJYBAAAAAAAAAAGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAYWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYBAAAAAAAAAAGUaCFLAYWUaBV0lFKUjApfbnBfcmFuZG9tlIwUbnVtcHkucmFuZG9tLl9waWNrbGWUjBJfX3JhbmRvbXN0YXRlX2N0b3KUk5SMB01UMTk5MzeUaC2MFF9fYml0X2dlbmVyYXRvcl9jdG9ylJOUhpRSlH2UKIwNYml0X2dlbmVyYXRvcpSMB01UMTk5MzeUjAVzdGF0ZZR9lCiMA2tleZRoEiiWwAkAAAAAAAAAAACAU8KznIcDtZNy7Ktb6Oay8s+2gdrVBu9hoTFNoGu1zNkT5hifdJx5L8ilG4DEeQFJng9D5F3gGJOSE1XM1EopZNIIlb400J5EcnoD8K2/CnObez7pYLEG2nUDRQtufdYWausENGaDt/P1pS9p70JjQ7Vc98J3UsxGRDctCIlu0I6ud/sYtoBPe575TzLsEti5jl6FqRnKrj12LWcrQoCexe7HH/UiAV1LzyQPzBlSZERXmHCdCvUSF7XpWt47xP9BzzqxX7aH3TPYWImqos1/ez/JlLdsD0MfMZl9G2CQq7cHHRlM3sj7jroA9c+pGt4l/iAGpRb80HbjwU71ykPTAVp531BXrc2qmIU6z9Fh4TAPx7fZ1kVF+L1Irlou+4Ckky7Ys59nB7KkciTI+N5jlb62ybZt0+ZWgIA6LKLvdx/mTQtB4k1aplT/C7L9/ybKCFn2quN/7YlIkxoH1U0xdabG6rgOrR+SHMmvUwvtKB+19Ibb07mSgVQyjNAvnyADPJf3pkxylZtn7f/OVpWEaWfl6BcLwy0grrEgUK+H+8P8XWMuBginXgwzn3sy4+ZOlr45op6TtuqX0Knz/SySGDlBIK8JqKObzB6fGt+ovJHEM8KlL4veKwkLkuuMWBaex3FBdWskry5qhslxMgnk2thh8DaXmAfbuI8j0SqHMW1kleITi9ekfXx/eSi5hX1GjA/M62Zixuay1H8zH9VjsTRcGacyJ0vh1hNReDFoNsXFbLfLqaIvbLDQjY7T289ZXsupvAxu2GVTbqWst+ckPPzwH7vLikULC+weAKwxarqm+ugAXgyz774meHOsvQYuu18nvrrunjZWDvwaKuYohEwUfSnpotE9XhX99yUTc8sGPQidTfXkzm/t8MWP8it4l4VSEgDLn8GW8t2DAh8EwFa/KOGoZEGjYqZ2IMA70E+F2LqgaZlQLFMONTIx3yuN5F2e1MT4v2wdBRK9R+lGMpxIiNldyOwwxLDBTRDMhd7APidmDwQBnvaIecKFa95btwHkRBEUT5g++/I0DDg685EX4OMO2YtTPqM3PQluS4puEhAQRVukNGSh4gYDgcBPKZl4ThNf+G+E7El9fmWJcP39Sifw6Mn+GEisM1RhHY05XZHUv5W4r8kD2jSLMY+IIL2+LtQrW7it7y28+sEicLoEfYOky9ZJF6l0fR+sXEawf+REH9LvtRJ4yzfxr7KisNpr1axv1ae5CDXS+XTzuOG/BJnHvt8arnY1XWH9SdkCOeok6MI8GBCtjTCxJ5JbpI5J0i0A66mJaRW9LMfP6Cil3/cVRQ9uN2KTtV3o7rJwY4XCnj7DJmqrUwofDDl7Ek0PoN7w0Hh8YHOy8qhPw7V8ALdjZn7eYtjCQIldQvHbM1I73RtCLQvQGFMXUCJ022pGRqTvZX5XWSizqbgX6TJmI6LDF9wcpYealB7cDwelfqdpzHRmyjRbIX9b+w4uj//aDRgP2SgiOAq/D/9/0SbgK/E0FQyclhNVAkbKwXhAxKGczpvJow0mFFUAt/5fT5KAsmQTAt8p0FsrGMDTfk4RzZgqZSm+ihVRS371Tx3twpGA1goo/AIfJh8slJC3hkR1OGCN7LAPGCwbM9rHlKSU4uuhJiff196h9q1kPMld6989MfKLVkvCl7ofCRurPUW46ceJKE951sQD1v8cK0HK1JmuBTCXAelCUCIFNLGk3tMXNVmuuFF3o3xb4V4T1IAYIfBdyEVHhIIZOE/JEY79daQw8njYEtQ6YwZ6kNCBYfrjq2OglITcRdwDmINL42ro6HnbWgLZQ8Ce/EiPVBtWHwhvGUHK1FNONzRzXgT1zKEg+WAigeuK4QVIxdITM4YvUyYvpQJuJd+xGD1no7BYIKXdV4aDlsRnWSMmS+zTyTvC0+TgBMCNpMvdChjaB/XTrMVsm0vgPmCYswn067MTYWfm5oCqqmNciqoRfFL2O2mxFT1VMcKDrxHBdBUhSG5UmAerx86KAEytbsCbn6OOj8Y02VwVynzXd0WJfLioeGMZISM1eneWfTc1mQ6CpdDxJqUmU86/KsBL3Bb0S2NAqFysFJZKxDwLej8xz+xH8IxEHzlkiiNH+2IIq0663FAwi6wg6dgcryDqQ+lNDwn898nylrcYShigDrtrFBNezKx3ZjpkPCnPUeQB4hJUrYCUJy5CyytC/x1UsByKez/aSNEWnlWnzYdJf2PoKL0YfmaR3KpXzi9ax3BHPgk1cdmgdVkqevFJ0DUdTBFQj/mhaKqcaT0rKJLgy/11AhWW4nX7+kAdgR0b1iAseI0TbMDtohBuqqUZfqMfUKsdI8v2aeUd0+IqOjPBFe7TZRC7OUYmf789SRTpw9gst4tzx7tLap8JnFt2keKhqd3vBgqpvlsxvx0DcPC+bo/qIldKiAn5D7TPjeWLzJ1gmpk1mVKOyWOv/ZzlRTfe8yEsMsRcgdPxbOuxLjlOwo1uFh9NjHoOz/xbnI62I49ZzT59GUCNtAL74UqjlRoyXZ5ELEjhTn+F5fYfEkY2TnSsgKO4Wwb/xD41S4mBL7LcUyF76ybV7Yx0L6V2QGoSfyhHFqMQJs/haLPPW18mWJb/UDl90ZN9TEzcdXvZsmCeqzCagC6YDHp3fop+5nAQSnT/Byt2j7z+6cnl/aZh6oKs5xrEMmuzpLFbXNVof9hNmX5E0DQ2M8uBqqeW95p6z8ySnOxURAO28oYWsbVyeYaNlWLZrOtIMZDRjjbecSSwMLlrBhw4mZVht4DgOQxI1+P7sPHZLMf89U+5ctf1rD0r1AXgyXjzOxKvCxWMhrz6Ah19+zal/bAIpw+0V7Pq85PRQO4UeScmMwODR8jcOfILuMmo7xXhemY/JqtOncklEaGapMeGlkiefvQkx9L5EWvLn6stI4zRP4pZXx9iOz17IKJmKOVHgCIAOiheb0bwkjNkItlfYO3LzeLLPuBDNLFg7tQu5NPWy28a4nBsE/gsyEteRvF2ECYFIOJg06dzc77IWw7o+z1Q5APxLg9uvyFniYWNuJyk7rflLCmYcg1gN657CWff8YfPr0ukKOamco94X1nFdyroxHiQlRXaP91DOqMueI1pCasyRQt0jtbWwxdEVyzP3GzUZXBWqa0xXCzwe29cxg2aiwKuuAAVfaCE/Pt1cJXq8wvliF81sMDPMbowd9+uyWuExq/e+2W3wWeV3hVofoiEySjBrJPWVJW9++UocJbC0ppNw5mtHktkZqUk6kVtUgVQ4Cj4udj/bluZzcqWjIvOCJO52M+xcQY808Ei8T/lwwS9TguuzQ3e0KR7hptgNcX1/XhCvAuUaAeMAnU0lImIh5RSlChLA2gLTk5OSv////9K/////0sAdJRiTXAChZRoFXSUUpSMA3Bvc5RNcAJ1jAloYXNfZ2F1c3OUSwCMBWdhdXNzlEcAAAAAAAAAAHVidWIu",
+        "dtype": "float32",
+        "_shape": [
+            1
+        ],
+        "low": "[-1.]",
+        "high": "[1.]",
+        "bounded_below": "[ True]",
+        "bounded_above": "[ True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 50016,
+    "_total_timesteps": 50000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1670943695022008941,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/MountainCarContinuous-v0__sac__1826025095__1670943692/MountainCarContinuous-v0",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVfQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAKYUF78kmwa8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwKGlIwBQ5R0lFKULg=="
+    },
+    "_episode_num": 338,
+    "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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_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:": "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 0x7f08a7f6a430>",
+        "add": "<function ReplayBuffer.add at 0x7f08a7f6a4c0>",
+        "sample": "<function ReplayBuffer.sample at 0x7f08a7f6a550>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f08a7f6a5e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f08a7f60f00>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLIGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "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,
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": []
+}

sac-MountainCarContinuous-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:201e49321c2558026b8665dd29d03b51e338d95a609086dfe24d48acc5e9fd7b
+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-5.19.0-32-generic-x86_64-with-glibc2.35 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 30 17:03:34 UTC 2
+- Python: 3.9.12
+- Stable-Baselines3: 1.8.0a6
+- PyTorch: 1.13.1+cu117
+- GPU Enabled: True
+- Numpy: 1.24.1
+- Gym: 0.21.0

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9e69be736c027f2b8b66097d76b45ac28d15d0ab0347671501a71a94a2c9680
+size 10233