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 +1,69 @@
+---
+library_name: stable-baselines3
+tags:
+- Pendulum-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Pendulum-v1
+      type: Pendulum-v1
+    metrics:
+    - type: mean_reward
+      value: -184.35 +/- 106.90
+      name: mean_reward
+      verified: false
+---
+
+# **SAC** Agent playing **Pendulum-v1**
+This is a trained model of a **SAC** agent playing **Pendulum-v1**
+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 Pendulum-v1 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo sac --env Pendulum-v1  -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 Pendulum-v1 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo sac --env Pendulum-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo sac --env Pendulum-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo sac --env Pendulum-v1 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('learning_rate', 0.001),
+             ('n_timesteps', 20000),
+             ('policy', 'MlpPolicy'),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - sac
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - Pendulum-v1
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - 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
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 3135132532
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - track
+    - false
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - sb3
+  - - yaml_file
+    - null

config.yml

@@ -0,0 +1,7 @@
+!!python/object/apply:collections.OrderedDict
+- - - learning_rate
+    - 0.001
+  - - n_timesteps
+    - 20000
+  - - policy
+    - MlpPolicy

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f5d45adaf37b39a1751a7b205c7f9299bea41f821ea44c877877db12e6e6db0
+size 143797

results.json

@@ -0,0 +1 @@
+{"mean_reward": -184.35301469999996, "std_reward": 106.89944811657462, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T15:36:56.513896"}

sac-Pendulum-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:219eae69f24402e123c2d00c6ced8d07f887c913fb98f1ff062bd827637a89b2
+size 3012413

sac-Pendulum-v1/_stable_baselines3_version

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

sac-Pendulum-v1/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c1f34c36b7a1a89a728424d9d6ab4dd4ec89b0b8ceca5ea5e432cf2cc190424
+size 545181

sac-Pendulum-v1/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a4474061898855d9b1e994c4fb91efc4c3f50beafa3ffd34c2929aedbfd1f2f
+size 1086969

sac-Pendulum-v1/data

@@ -0,0 +1,117 @@
+{
+    "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 0x7f6c739d1ca0>",
+        "_build": "<function SACPolicy._build at 0x7f6c739d1d30>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7f6c739d1dc0>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7f6c739d1e50>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7f6c739d1ee0>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7f6c739d1f70>",
+        "forward": "<function SACPolicy.forward at 0x7f6c739da040>",
+        "_predict": "<function SACPolicy._predict at 0x7f6c739da0d0>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7f6c739da160>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f6c73ebedc0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "use_sde": false
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            3
+        ],
+        "low": "[-1. -1. -8.]",
+        "high": "[1. 1. 8.]",
+        "bounded_below": "[ True  True  True]",
+        "bounded_above": "[ True  True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            1
+        ],
+        "low": "[-2.]",
+        "high": "[2.]",
+        "bounded_below": "[ True]",
+        "bounded_above": "[ True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 20000,
+    "_total_timesteps": 20000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1671719869860530827,
+    "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:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYMAAAAAAAAAClpfj+L2OM91obOvZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsDhpSMAUOUdJRSlC4="
+    },
+    "_episode_num": 100,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVHRAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIxlBOtPtTlMCUhpRSlIwBbJRLyIwBdJRHQAUDx9XtBv91fZQoaAZoCWgPQwhn8zgMVkabwJSGlFKUaBVLyGgWR0AS+zJIUahpdX2UKGgGaAloD0MImE9WDLeklcCUhpRSlGgVS8hoFkdAG4zo2XLNfXV9lChoBmgJaA9DCNgRh2zgBJzAlIaUUpRoFUvIaBZHQCH6GgzxgAp1fZQoaAZoCWgPQwgg7X+AdS+ZwJSGlFKUaBVLyGgWR0AmQI2OyVv/dX2UKGgGaAloD0MI6NoX0GvamcCUhpRSlGgVS8hoFkdAKm3g9/z8QHV9lChoBmgJaA9DCITU7ezr85bAlIaUUpRoFUvIaBZHQC6artE5Qxh1fZQoaAZoCWgPQwhfl+E/vfKPwJSGlFKUaBVLyGgWR0Axb/i5uqFRdX2UKGgGaAloD0MIS1tc40M9kcCUhpRSlGgVS8hoFkdAM4d6LOzIFXV9lChoBmgJaA9DCIyDS8eceIzAlIaUUpRoFUvIaBZHQDWbcQAdXDF1fZQoaAZoCWgPQwiZKELqlpSJwJSGlFKUaBVLyGgWR0A3yZQHiWE9dX2UKGgGaAloD0MI6fF7m15AgMCUhpRSlGgVS8hoFkdAOdu+mFaje3V9lChoBmgJaA9DCKiMf59xofm/lIaUUpRoFUvIaBZHQDvxWp6yB091fZQoaAZoCWgPQwgmOPWBtN2UwJSGlFKUaBVLyGgWR0A+Cp84PwuvdX2UKGgGaAloD0MI+mGE8KhlcMCUhpRSlGgVS8hoFkdAQBDMC9ytFXV9lChoBmgJaA9DCLTIdr4fgm/AlIaUUpRoFUvIaBZHQEEd+T/yXld1fZQoaAZoCWgPQwimR1M9mWt2wJSGlFKUaBVLyGgWR0BCLGhEjPfLdX2UKGgGaAloD0MI6nqi60JaYMCUhpRSlGgVS8hoFkdARYxiAlOXV3V9lChoBmgJaA9DCMLfL2ZLdmDAlIaUUpRoFUvIaBZHQElos9SuQp51fZQoaAZoCWgPQwhKmGn7Vz14wJSGlFKUaBVLyGgWR0BNPi/wiJO4dX2UKGgGaAloD0MIhzWVReFwbcCUhpRSlGgVS8hoFkdAUJDd9Dx9X3V9lChoBmgJaA9DCGGowwq34V7AlIaUUpRoFUvIaBZHQFD9IAwPAfx1fZQoaAZoCWgPQwhDN/sD5VYXwJSGlFKUaBVLyGgWR0BRZfS2H+IedX2UKGgGaAloD0MIBtUGJ6INcMCUhpRSlGgVS8hoFkdAUc/Kq4pc5nV9lChoBmgJaA9DCP/NixMfdpHAlIaUUpRoFUvIaBZHQFI5Mpw0fo11fZQoaAZoCWgPQwjwbfqzfySEwJSGlFKUaBVLyGgWR0BSoirYGt6pdX2UKGgGaAloD0MI6gjgZvHpXcCUhpRSlGgVS8hoFkdAUw4daMaS93V9lChoBmgJaA9DCPinVImyLW7AlIaUUpRoFUvIaBZHQFN4/L1VYIV1fZQoaAZoCWgPQwgO2xZlNnBfwJSGlFKUaBVLyGgWR0BT4uDWbwz+dX2UKGgGaAloD0MICqGDLmFZYMCUhpRSlGgVS8hoFkdAVEWHck+otXV9lChoBmgJaA9DCJROJJhqdl7AlIaUUpRoFUvIaBZHQFSvnAIppex1fZQoaAZoCWgPQwgi+rX103/vv5SGlFKUaBVLyGgWR0BVGcIeHSF5dX2UKGgGaAloD0MIRYE+kSfPXsCUhpRSlGgVS8hoFkdAVYDxtpEhJXV9lChoBmgJaA9DCGxaKQRyL2/AlIaUUpRoFUvIaBZHQFXsm3fAKv51fZQoaAZoCWgPQwihndMs0G70v5SGlFKUaBVLyGgWR0BWUnUQTVUddX2UKGgGaAloD0MIUFQ2rKnhXsCUhpRSlGgVS8hoFkdAVrgcU/OdG3V9lChoBmgJaA9DCKIpO/2g3F/AlIaUUpRoFUvIaBZHQFclL9uP3i91fZQoaAZoCWgPQwg7j4r/O59fwJSGlFKUaBVLyGgWR0BXjxSgoPTYdX2UKGgGaAloD0MItKz7x8IFYMCUhpRSlGgVS8hoFkdAV/WXa8Hv+nV9lChoBmgJaA9DCIR/ETRmUgHAlIaUUpRoFUvIaBZHQFhbWMS9M9N1fZQoaAZoCWgPQwjcL5+sGA4AwJSGlFKUaBVLyGgWR0BYxUU9IPK/dX2UKGgGaAloD0MIQtKnVfTsXcCUhpRSlGgVS8hoFkdAWTCuOjqOcXV9lChoBmgJaA9DCNAM4gM7GV/AlIaUUpRoFUvIaBZHQFmaczqKP4p1fZQoaAZoCWgPQwgVkWEVbydfwJSGlFKUaBVLyGgWR0BaB7BsQ/X5dX2UKGgGaAloD0MIAB5RoTrXbMCUhpRSlGgVS8hoFkdAWm19Tgl4T3V9lChoBmgJaA9DCJp7SPjeHV7AlIaUUpRoFUvIaBZHQFrMSlnAZbZ1fZQoaAZoCWgPQwg5J/bQPu5ewJSGlFKUaBVLyGgWR0BbMZUcXFcZdX2UKGgGaAloD0MIFi8Whsj4XcCUhpRSlGgVS8hoFkdAW6EkdFOO83V9lChoBmgJaA9DCGKE8Gjj4l7AlIaUUpRoFUvIaBZHQFwSIF/x2B91fZQoaAZoCWgPQwjpnJ/iOGFswJSGlFKUaBVLyGgWR0BcfAla8pTddX2UKGgGaAloD0MI4s0avK8ybMCUhpRSlGgVS8hoFkdAXOmUgSvkinV9lChoBmgJaA9DCNyBOuXR3F3AlIaUUpRoFUvIaBZHQF1QHMUypJh1fZQoaAZoCWgPQwjsMCb9PTNgwJSGlFKUaBVLyGgWR0BdujTa0x/NdX2UKGgGaAloD0MIeSCySJMbYMCUhpRSlGgVS8hoFkdAXiTuNPxhD3V9lChoBmgJaA9DCDttjQjG72zAlIaUUpRoFUvIaBZHQF6S8pkPMB91fZQoaAZoCWgPQwhLy0i9p+xrwJSGlFKUaBVLyGgWR0Be/78m8dxRdX2UKGgGaAloD0MI6dMq+kPZXsCUhpRSlGgVS8hoFkdAX2sY51eSjnV9lChoBmgJaA9DCFuZ8Ev96V/AlIaUUpRoFUvIaBZHQF/VENvwVj91fZQoaAZoCWgPQwi5isVvCnRtwJSGlFKUaBVLyGgWR0BgGi88La24dX2UKGgGaAloD0MIDmq/tRM6XcCUhpRSlGgVS8hoFkdAYFCbZvkzXXV9lChoBmgJaA9DCCxF8pXAcW7AlIaUUpRoFUvIaBZHQGCHswco6S11fZQoaAZoCWgPQwihhm9h3Tj1v5SGlFKUaBVLyGgWR0Bgu2J53TuwdX2UKGgGaAloD0MIqWkX00wPX8CUhpRSlGgVS8hoFkdAYPA5YHPeHnV9lChoBmgJaA9DCIl9AihGiV/AlIaUUpRoFUvIaBZHQGEm28AaNuN1fZQoaAZoCWgPQwitTPilfh5ewJSGlFKUaBVLyGgWR0BhWhJGvwEydX2UKGgGaAloD0MIh/wzg/iTX8CUhpRSlGgVS8hoFkdAYZA+5e7cwnV9lChoBmgJaA9DCBOB6h9EKV3AlIaUUpRoFUvIaBZHQGHGMuFpPAR1fZQoaAZoCWgPQwi3tvC8VDldwJSGlFKUaBVLyGgWR0Bh9pjlPrOadX2UKGgGaAloD0MI+OC1SxvJXcCUhpRSlGgVS8hoFkdAYiZU4JeE7HV9lChoBmgJaA9DCDqt26D2OwfAlIaUUpRoFUvIaBZHQGJWC3ocJdB1fZQoaAZoCWgPQwgibeNPVDb7v5SGlFKUaBVLyGgWR0BiheN96TnrdX2UKGgGaAloD0MIhGIraFodbMCUhpRSlGgVS8hoFkdAYrWr7wazeHV9lChoBmgJaA9DCPyKNVzkN2DAlIaUUpRoFUvIaBZHQGLlkKmbb111fZQoaAZoCWgPQwhpkIKnEAtgwJSGlFKUaBVLyGgWR0BjFVwm3OObdX2UKGgGaAloD0MIpP0PsFZtC8CUhpRSlGgVS8hoFkdAY0Vnxri2lXV9lChoBmgJaA9DCOF9VS5U8F7AlIaUUpRoFUvIaBZHQGN1cdYGMXJ1fZQoaAZoCWgPQwi+EkiJ3c5twJSGlFKUaBVLyGgWR0BjpXq/ub7TdX2UKGgGaAloD0MIaW6FsBpYXsCUhpRSlGgVS8hoFkdAY9Vtnf2saXV9lChoBmgJaA9DCJ5DGapiil7AlIaUUpRoFUvIaBZHQGQGDgAIY3x1fZQoaAZoCWgPQwjpDfeRWwduwJSGlFKUaBVLyGgWR0BkNsxwhnrZdX2UKGgGaAloD0MIdqT6zi87XcCUhpRSlGgVS8hoFkdAZGelTFVDKHV9lChoBmgJaA9DCAuZK4Nq1V7AlIaUUpRoFUvIaBZHQGSXytV7x/d1fZQoaAZoCWgPQwirkzMU95pswJSGlFKUaBVLyGgWR0Bkx+PcSGrTdX2UKGgGaAloD0MIIjmZuFULbcCUhpRSlGgVS8hoFkdAZPf6k690zXV9lChoBmgJaA9DCHfaGhGMowLAlIaUUpRoFUvIaBZHQGUn+AuqWC51fZQoaAZoCWgPQwhYAb7bvPELwJSGlFKUaBVLyGgWR0BlVgFC9h7WdX2UKGgGaAloD0MIu9QI/UwYbsCUhpRSlGgVS8hoFkdAZYWkzoEB83V9lChoBmgJaA9DCGiVmdL6717AlIaUUpRoFUvIaBZHQGW12SMcZLt1fZQoaAZoCWgPQwi2EOSghD5swJSGlFKUaBVLyGgWR0Bl5g6EJ0GNdX2UKGgGaAloD0MI+imOAy+CbsCUhpRSlGgVS8hoFkdAZhZYFJQLu3V9lChoBmgJaA9DCM+9h0uOyF3AlIaUUpRoFUvIaBZHQGZGRgZ0jkd1fZQoaAZoCWgPQwhkdavnpMpfwJSGlFKUaBVLyGgWR0BmeFC/oJRgdX2UKGgGaAloD0MIUPutnajZbsCUhpRSlGgVS8hoFkdAZqsNpdrwfHV9lChoBmgJaA9DCBfVIqKY0W3AlIaUUpRoFUvIaBZHQGbbQ71ZkkN1fZQoaAZoCWgPQwiKzce1IXlswJSGlFKUaBVLyGgWR0BnDQ+wC8vmdX2UKGgGaAloD0MIUtFY+ztiX8CUhpRSlGgVS8hoFkdAZz1lbNbC8HV9lChoBmgJaA9DCBf1Se6wNl/AlIaUUpRoFUvIaBZHQGdzIvrWy1N1fZQoaAZoCWgPQwggYK3aNYNdwJSGlFKUaBVLyGgWR0BnqPvc8DB/dX2UKGgGaAloD0MIIjXtYppEX8CUhpRSlGgVS8hoFkdAZ9xiaRZED3V9lChoBmgJaA9DCA1wQbYsZF3AlIaUUpRoFUvIaBZHQGgPU2DQJHB1ZS4="
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 19900,
+    "buffer_size": 1,
+    "batch_size": 256,
+    "learning_starts": 100,
+    "tau": 0.005,
+    "gamma": 0.99,
+    "gradient_steps": 1,
+    "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 0x7f6c73a2a430>",
+        "add": "<function ReplayBuffer.add at 0x7f6c73a2a4c0>",
+        "sample": "<function ReplayBuffer.sample at 0x7f6c73a2a550>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f6c73a2a5e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f6c73a24340>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -1.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": []
+}

sac-Pendulum-v1/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db4fc07e27a0bf9a552bd24c2cb901d3341ba0ea28c1f17288c3467b2c63e721
+size 1507

sac-Pendulum-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ea82ef1c6f1d6bbbb8d5adb31ebb4220e69d3282276f48f3b522ec430863e26
+size 1357573

sac-Pendulum-v1/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42cb208f9dd5b76d605718ce3d07fdd416c6739e351af12aa5357c23b43db6a0
+size 747

sac-Pendulum-v1/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:b5d5f14350ebdd6436351c3f9e87e4e0e54e0e8d9c53816fc90c8bb6646133c4
+size 2918