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 +1,71 @@
+---
+library_name: stable-baselines3
+tags:
+- Walker2d-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TD3
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Walker2d-v3
+      type: Walker2d-v3
+    metrics:
+    - type: mean_reward
+      value: 4293.94 +/- 45.25
+      name: mean_reward
+      verified: false
+---
+
+# **TD3** Agent playing **Walker2d-v3**
+This is a trained model of a **TD3** agent playing **Walker2d-v3**
+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 td3 --env Walker2d-v3 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo td3 --env Walker2d-v3  -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 td3 --env Walker2d-v3 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo td3 --env Walker2d-v3  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo td3 --env Walker2d-v3 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo td3 --env Walker2d-v3 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('learning_starts', 10000),
+             ('n_timesteps', 1000000.0),
+             ('noise_std', 0.1),
+             ('noise_type', 'normal'),
+             ('policy', 'MlpPolicy'),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,83 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - td3
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - Walker2d-v3
+  - - 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
+    - 542522677
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/Walker2d-v3__td3__542522677__1676676142
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - openrlbenchmark
+  - - wandb_project_name
+    - sb3
+  - - wandb_tags
+    - []
+  - - yaml_file
+    - null

config.yml

@@ -0,0 +1,11 @@
+!!python/object/apply:collections.OrderedDict
+- - - learning_starts
+    - 10000
+  - - n_timesteps
+    - 1000000.0
+  - - noise_std
+    - 0.1
+  - - noise_type
+    - normal
+  - - policy
+    - MlpPolicy

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2871cbabf575b8e4898c40bd2e327cf1510b0bef29e3578ad1ae10dffb6ec3b1
+size 1257119

results.json

@@ -0,0 +1 @@
+{"mean_reward": 4293.9378676, "std_reward": 45.24701851960837, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T17:37:32.918336"}

td3-Walker2d-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a490c5cb202acefc4fa152dba9ed42be1be6e5141e48789532c699f0db8d80
+size 6282634

td3-Walker2d-v3/_stable_baselines3_version

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

td3-Walker2d-v3/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eb9e08e1c85f91f3b4e219eb7cc9d9a9a5268b955dc59189e8c1cc9af422fa3
+size 1039279

td3-Walker2d-v3/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55272ab872fd8ff03065638d09765e69e62b271ff3c8cbd9c663f70e8814cfc6
+size 2092601

td3-Walker2d-v3/data

@@ -0,0 +1,118 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnRkMy5wb2xpY2llc5SMCVREM1BvbGljeZSTlC4=",
+        "__module__": "stable_baselines3.td3.policies",
+        "__doc__": "\n    Policy class (with both actor and critic) for TD3.\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 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 TD3Policy.__init__ at 0x7f1ced9f0af0>",
+        "_build": "<function TD3Policy._build at 0x7f1ced9f0b80>",
+        "_get_constructor_parameters": "<function TD3Policy._get_constructor_parameters at 0x7f1ced9f0c10>",
+        "make_actor": "<function TD3Policy.make_actor at 0x7f1ced9f0ca0>",
+        "make_critic": "<function TD3Policy.make_critic at 0x7f1ced9f0d30>",
+        "forward": "<function TD3Policy.forward at 0x7f1ced9f0dc0>",
+        "_predict": "<function TD3Policy._predict at 0x7f1ced9f0e50>",
+        "set_training_mode": "<function TD3Policy.set_training_mode at 0x7f1ced9f0ee0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f1ced9f6200>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float64",
+        "_shape": [
+            17
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False False False False False\n False False False False False]",
+        "bounded_above": "[False False False False False False False False False False False False\n False False False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWVNgwAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLBoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWGAAAAAAAAAAAAIC/AACAvwAAgL8AAIC/AACAvwAAgL+UaApLBoWUjAFDlHSUUpSMBGhpZ2iUaBIolhgAAAAAAAAAAACAPwAAgD8AAIA/AACAPwAAgD8AAIA/lGgKSwaFlGgVdJRSlIwNYm91bmRlZF9iZWxvd5RoEiiWBgAAAAAAAAABAQEBAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLBoWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYGAAAAAAAAAAEBAQEBAZRoIUsGhZRoFXSUUpSMCl9ucF9yYW5kb22UjBRudW1weS5yYW5kb20uX3BpY2tsZZSMEl9fcmFuZG9tc3RhdGVfY3RvcpSTlIwHTVQxOTkzN5RoLYwUX19iaXRfZ2VuZXJhdG9yX2N0b3KUk5SGlFKUfZQojA1iaXRfZ2VuZXJhdG9ylIwHTVQxOTkzN5SMBXN0YXRllH2UKIwDa2V5lGgSKJbACQAAAAAAAAAAAIBTwrOchwO1k3Lsq1vo5rLyz7aB2tUG72GhMU2ga7XM2RPmGJ90nHkvyKUbgMR5AUmeD0PkXeAYk5ITVczUSilk0giVvjTQnkRyegPwrb8Kc5t7PulgsQbadQNFC2591hZq6wQ0ZoO38/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": [
+            6
+        ],
+        "low": "[-1. -1. -1. -1. -1. -1.]",
+        "high": "[1. 1. 1. 1. 1. 1.]",
+        "bounded_below": "[ True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 1000213,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": {
+        ":type:": "<class 'stable_baselines3.common.noise.NormalActionNoise'>",
+        ":serialized:": "gAWVOgEAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5ub2lzZZSMEU5vcm1hbEFjdGlvbk5vaXNllJOUKYGUfZQojANfbXWUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWMAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwaFlIwBQ5R0lFKUjAZfc2lnbWGUaAgoljAAAAAAAAAAmpmZmZmZuT+amZmZmZm5P5qZmZmZmbk/mpmZmZmZuT+amZmZmZm5P5qZmZmZmbk/lGgPSwaFlGgTdJRSlHViLg==",
+        "_mu": "[0. 0. 0. 0. 0. 0.]",
+        "_sigma": "[0.1 0.1 0.1 0.1 0.1 0.1]"
+    },
+    "start_time": 1676676145105982284,
+    "learning_rate": 0.001,
+    "tensorboard_log": "runs/Walker2d-v3__td3__542522677__1676676142/Walker2d-v3",
+    "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:": "gAWV/QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaIAAAAAAAAAOUwiz9ND/M/CRMKETVS0T93dlvtSRSaP8IRb6fliKW/JBZOaWndv7+aFI50kq32v8egdf5dQow/shhqwyht6r/pW3TVHhQLQNXh7IXGCt2/jssz+rH9AcBdvM68PGbHvzZhrcTmjB/AAAAAAAAAJMBPTzY+fDkCwEzXBRsiSry/axoM1NMzp7+UjAVudW1weZSMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLEYaUjAFDlHSUUpQu"
+    },
+    "_episode_num": 2886,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.00021300000000001873,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 990215,
+    "buffer_size": 1,
+    "batch_size": 100,
+    "learning_starts": 10000,
+    "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 0x7f1ced9ed5e0>",
+        "add": "<function ReplayBuffer.add at 0x7f1ced9ed670>",
+        "sample": "<function ReplayBuffer.sample at 0x7f1ced9ed700>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f1ced9ed790>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f1ced9e4fc0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVZAAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMB2VwaXNvZGWUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "policy_delay": 2,
+    "target_noise_clip": 0.5,
+    "target_policy_noise": 0.2,
+    "actor_batch_norm_stats": [],
+    "critic_batch_norm_stats": [],
+    "actor_batch_norm_stats_target": [],
+    "critic_batch_norm_stats_target": []
+}

td3-Walker2d-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3c1df52fed3753576a66a3cdd406db1940453b29346bba4980bc792c9b5cca1
+size 3129721

td3-Walker2d-v3/pytorch_variables.pth

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

td3-Walker2d-v3/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 sha256:279329808252a70c80ee9abb7c9ed64a59c8e7c63b0bf033db64abf7e376f613
+size 91436