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:
+- Hopper-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TRPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Hopper-v3
+      type: Hopper-v3
+    metrics:
+    - type: mean_reward
+      value: 3740.10 +/- 4.38
+      name: mean_reward
+      verified: false
+---
+
+# **TRPO** Agent playing **Hopper-v3**
+This is a trained model of a **TRPO** agent playing **Hopper-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 trpo --env Hopper-v3 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo trpo --env Hopper-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 trpo --env Hopper-v3 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo trpo --env Hopper-v3  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo trpo --env Hopper-v3 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo trpo --env Hopper-v3 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 128),
+             ('cg_damping', 0.1),
+             ('cg_max_steps', 25),
+             ('gae_lambda', 0.95),
+             ('gamma', 0.99),
+             ('learning_rate', 0.001),
+             ('n_critic_updates', 20),
+             ('n_envs', 2),
+             ('n_steps', 1024),
+             ('n_timesteps', 1000000.0),
+             ('normalize', True),
+             ('policy', 'MlpPolicy'),
+             ('sub_sampling_factor', 1),
+             ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
+```

args.yml

@@ -0,0 +1,83 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - trpo
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - Hopper-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
+    - 3310923026
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/Hopper-v3__trpo__3310923026__1675873637
+  - - 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 +1,27 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 128
+  - - cg_damping
+    - 0.1
+  - - cg_max_steps
+    - 25
+  - - gae_lambda
+    - 0.95
+  - - gamma
+    - 0.99
+  - - learning_rate
+    - 0.001
+  - - n_critic_updates
+    - 20
+  - - n_envs
+    - 2
+  - - n_steps
+    - 1024
+  - - n_timesteps
+    - 1000000.0
+  - - normalize
+    - true
+  - - policy
+    - MlpPolicy
+  - - sub_sampling_factor
+    - 1

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4452129025e0f4d301b05ad9711586963d187a5a873da06458aa7fa3b13aa47a
+size 1464156

results.json

@@ -0,0 +1 @@
+{"mean_reward": 3740.1029797, "std_reward": 4.379330216585682, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T13:56:47.478332"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d399fad8010438f0154e9621c592824352d7a37db7b6fb706d9c157dd50ae2ee
+size 75776

trpo-Hopper-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d37cb3355b8a5d82dcdd07f5d8f541ab0da469aa2a4a6b04f98390932befa7c
+size 110186

trpo-Hopper-v3/_stable_baselines3_version

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

trpo-Hopper-v3/data

@@ -0,0 +1,103 @@
+{
+    "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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7f13c90d1ee0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f13c90d1f70>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f13c90d4040>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f13c90d40d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f13c90d4160>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f13c90d41f0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f13c90d4280>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f13c90d4310>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f13c90d43a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f13c90d4430>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f13c90d44c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f13c90d4550>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f13c949bcc0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float64",
+        "_shape": [
+            11
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWVGAwAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLA4WUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWDAAAAAAAAAAAAIC/AACAvwAAgL+UaApLA4WUjAFDlHSUUpSMBGhpZ2iUaBIolgwAAAAAAAAAAACAPwAAgD8AAIA/lGgKSwOFlGgVdJRSlIwNYm91bmRlZF9iZWxvd5RoEiiWAwAAAAAAAAABAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLA4WUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYDAAAAAAAAAAEBAZRoIUsDhZRoFXSUUpSMCl9ucF9yYW5kb22UjBRudW1weS5yYW5kb20uX3BpY2tsZZSMEl9fcmFuZG9tc3RhdGVfY3RvcpSTlIwHTVQxOTkzN5RoLYwUX19iaXRfZ2VuZXJhdG9yX2N0b3KUk5SGlFKUfZQojA1iaXRfZ2VuZXJhdG9ylIwHTVQxOTkzN5SMBXN0YXRllH2UKIwDa2V5lGgSKJbACQAAAAAAAAAAAIBTwrOchwO1k3Lsq1vo5rLyz7aB2tUG72GhMU2ga7XM2RPmGJ90nHkvyKUbgMR5AUmeD0PkXeAYk5ITVczUSilk0giVvjTQnkRyegPwrb8Kc5t7PulgsQbadQNFC2591hZq6wQ0ZoO38/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": [
+            3
+        ],
+        "low": "[-1. -1. -1.]",
+        "high": "[1. 1. 1.]",
+        "bounded_below": "[ True  True  True]",
+        "bounded_above": "[ True  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": 1675873641522805264,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/Hopper-v3__trpo__3310923026__1675873637/Hopper-v3",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYCAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksChZSMAUOUdJRSlC4="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVJQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJawAAAAAAAAAKSEN/kc+PM/kNUX80j6X7+QLLuGwEpTPxQUM4BvBm6/zxz/+jlVcT/zG8fmO9hzv+UerMTCCXG/sLPBZNS7Sr9ngKZRrURxP+bLeaXYD2A/AlBG16xHZD/zm8o7f/vzP/ULVsn5iHI/OJHvXMmUbL/I2cMNhuRWv4wLORO5GXS/YIcOYSEeRL9JriplNzhwP8JCInORZlS/RNtSZKUfcL+g23yBhvIjP40fC77s1GG/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksCSwuGlIwBQ5R0lFKULg=="
+    },
+    "_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": 489,
+    "n_steps": 1024,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
+    "vf_coef": 0.0,
+    "max_grad_norm": 0.0,
+    "normalize_advantage": true,
+    "batch_size": 128,
+    "cg_max_steps": 25,
+    "cg_damping": 0.1,
+    "line_search_shrinking_factor": 0.8,
+    "line_search_max_iter": 10,
+    "target_kl": 0.01,
+    "n_critic_updates": 20,
+    "sub_sampling_factor": 1
+}

trpo-Hopper-v3/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b662ef5c41a8e67ce7ad5772e4683dd876fa3fd3847158ca793f454f39ba010
+size 44975

trpo-Hopper-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac39a773ba50cdca7b6e9ff0aacceb5fd7bf82187451bcfe3249da6538247e99
+size 44926

trpo-Hopper-v3/pytorch_variables.pth

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

trpo-Hopper-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

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:438be8b961c49d96820156b37f58464c082f2fd87ade80051c64ed4011fae581
+size 4539