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:
+- Swimmer-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TRPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Swimmer-v3
+      type: Swimmer-v3
+    metrics:
+    - type: mean_reward
+      value: 151.17 +/- 2.55
+      name: mean_reward
+      verified: false
+---
+
+# **TRPO** Agent playing **Swimmer-v3**
+This is a trained model of a **TRPO** agent playing **Swimmer-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 Swimmer-v3 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo trpo --env Swimmer-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 Swimmer-v3 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo trpo --env Swimmer-v3  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo trpo --env Swimmer-v3 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo trpo --env Swimmer-v3 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 128),
+             ('cg_damping', 0.1),
+             ('cg_max_steps', 25),
+             ('gae_lambda', 0.95),
+             ('gamma', 0.9999),
+             ('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
+    - Swimmer-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
+    - 1116843116
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/Swimmer-v3__trpo__1116843116__1676735391
+  - - 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
+    - 0.9999
+  - - 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:cfbcdba5fa225a610f085f3be7886cc6e029afae924658fd64e2c04fd48bbaf7
+size 1255865

results.json

@@ -0,0 +1 @@
+{"mean_reward": 151.1700838, "std_reward": 2.553347956188885, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T16:16:43.981925"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c71c69fd76bbb29fb26c942a4fe5c0a354d507f583cf20a72e1c9be52c9f68a3
+size 42444

trpo-Swimmer-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01ed82af57e14f106d828a82b2394a24f2e6fc08ae5490ff3c368eb9973b2761
+size 106519

trpo-Swimmer-v3/_stable_baselines3_version

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

trpo-Swimmer-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 0x7f9cf9753ee0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9cf9753f70>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9cf9754040>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9cf97540d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f9cf9754160>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f9cf97541f0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f9cf9754280>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9cf9754310>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f9cf97543a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9cf9754430>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9cf97544c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9cf9754550>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f9cf9755100>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float64",
+        "_shape": [
+            8
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            2
+        ],
+        "low": "[-1. -1.]",
+        "high": "[1. 1.]",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ 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": 1676735395137327522,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/Swimmer-v3__trpo__1116843116__1676735391/Swimmer-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:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAAfhIxQS0qS/98Ug1v4Tsr+IFtkqfKOmP7reGSoD5au/ULzPj/zjgz99wuHWfqSyv6BboziEzW4/zKrlyESGqT9YYOgCmmy3v/CKsDDIE4O/9zchu2eiq79Q4NCv+Uh4PzKuRZSE/rY/2M+vXzighL9Ued78PWyevzrh57hN5KK/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksCSwiGlIwBQ5R0lFKULg=="
+    },
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.0014719999999999178,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVgRAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMInx1wXTHRYUCUhpRSlIwBbJRN6AOMAXSUR0CaCkgpjMFEdX2UKGgGaAloD0MIDM11Guk/Y0CUhpRSlGgVTegDaBZHQJoKQhzNliB1fZQoaAZoCWgPQwivd3+817xhQJSGlFKUaBVN6ANoFkdAmhgi/TLGJnV9lChoBmgJaA9DCEEtBg9Ty2FAlIaUUpRoFU3oA2gWR0CaGBztCzC2dX2UKGgGaAloD0MI1H/W/HhbYkCUhpRSlGgVTegDaBZHQJol8MKCxu91fZQoaAZoCWgPQwhmg0wycrlhQJSGlFKUaBVN6ANoFkdAmiXqyfL9uXV9lChoBmgJaA9DCAYv+gpSgmJAlIaUUpRoFU3oA2gWR0CaM4ISlFc6dX2UKGgGaAloD0MIEHnL1Q+uYUCUhpRSlGgVTegDaBZHQJozfAP/aQF1fZQoaAZoCWgPQwh7EALyJRdjQJSGlFKUaBVN6ANoFkdAmkI1biZOSHV9lChoBmgJaA9DCIl7LH1ohWJAlIaUUpRoFU3oA2gWR0CaQi9t/FzddX2UKGgGaAloD0MIcjJxqyBYY0CUhpRSlGgVTegDaBZHQJpQobhm5Dt1fZQoaAZoCWgPQwjqd2FrNrthQJSGlFKUaBVN6ANoFkdAmlCbxEv0y3V9lChoBmgJaA9DCNanHJNF9GFAlIaUUpRoFU3oA2gWR0CaXeNhmXgMdX2UKGgGaAloD0MIN8e5TTieYkCUhpRSlGgVTegDaBZHQJpd3U+cH4Z1fZQoaAZoCWgPQwgi/fZ1YONhQJSGlFKUaBVN6ANoFkdAmmvrCiyprHV9lChoBmgJaA9DCJqXw+67Q2NAlIaUUpRoFU3oA2gWR0Caa+T3IuGsdX2UKGgGaAloD0MIcJaS5SSMYkCUhpRSlGgVTegDaBZHQJp6qyprDZV1fZQoaAZoCWgPQwgOh6WBnwxiQJSGlFKUaBVN6ANoFkdAmnqlLJ0W/XV9lChoBmgJaA9DCIvh6gCI6WFAlIaUUpRoFU3oA2gWR0CaiIbIcR16dX2UKGgGaAloD0MID0QWaeKVYkCUhpRSlGgVTegDaBZHQJqIgMqjJuF1fZQoaAZoCWgPQwiPbK6aZ6ZhQJSGlFKUaBVN6ANoFkdAmpZfzFuNxXV9lChoBmgJaA9DCNo7o61KIGJAlIaUUpRoFU3oA2gWR0Callm7rcCYdX2UKGgGaAloD0MIYMlVLP59YkCUhpRSlGgVTegDaBZHQJqkcGNaQmx1fZQoaAZoCWgPQwhX0LTEygxiQJSGlFKUaBVN6ANoFkdAmqRqZML4OHV9lChoBmgJaA9DCGcPtAJDwmJAlIaUUpRoFU3oA2gWR0Caya9Ujs2OdX2UKGgGaAloD0MI17/rM+f2YUCUhpRSlGgVTegDaBZHQJrJqVdHDrJ1fZQoaAZoCWgPQwhycOmY87ViQJSGlFKUaBVN6ANoFkdAmtfX05EMLHV9lChoBmgJaA9DCD/FceBVKGJAlIaUUpRoFU3oA2gWR0Ca19HCGetkdX2UKGgGaAloD0MIrKjBNAyxYUCUhpRSlGgVTegDaBZHQJrmEILPUrl1fZQoaAZoCWgPQwjeHK7VnthhQJSGlFKUaBVN6ANoFkdAmuYKgM+eOHV9lChoBmgJaA9DCBprf2d7T2JAlIaUUpRoFU3oA2gWR0Ca85lar3j/dX2UKGgGaAloD0MIrfcb7bi4YkCUhpRSlGgVTegDaBZHQJrzk2Hck+p1fZQoaAZoCWgPQwifW+hKhANjQJSGlFKUaBVN6ANoFkdAmwEqpT/ACXV9lChoBmgJaA9DCInqrYGtn2JAlIaUUpRoFU3oA2gWR0CbASStvGZNdX2UKGgGaAloD0MIWK63zdTDYUCUhpRSlGgVTegDaBZHQJsO/H2h7E51fZQoaAZoCWgPQwj9ogT9BQRiQJSGlFKUaBVN6ANoFkdAmw72eg+Ql3V9lChoBmgJaA9DCNlg4SRNdWJAlIaUUpRoFU3oA2gWR0CbGj6wMYuTdX2UKGgGaAloD0MIM0+uKRD8YUCUhpRSlGgVTegDaBZHQJsaOJtSAH51fZQoaAZoCWgPQwjScTWyq95hQJSGlFKUaBVN6ANoFkdAmyHkJF9a2XV9lChoBmgJaA9DCKJCdXPxw2FAlIaUUpRoFU3oA2gWR0CbId4LThHcdX2UKGgGaAloD0MIvQFmvgMjYkCUhpRSlGgVTegDaBZHQJstkMDwH7h1fZQoaAZoCWgPQwgrTN9rCFdiQJSGlFKUaBVN6ANoFkdAmy2Kq814xHV9lChoBmgJaA9DCGSyuP9INmJAlIaUUpRoFU3oA2gWR0CbOObC79Q5dX2UKGgGaAloD0MIl8gFZ3BuY0CUhpRSlGgVTegDaBZHQJs44K0D2al1fZQoaAZoCWgPQwi/Q1GgT/JiQJSGlFKUaBVN6ANoFkdAm0bZpztCzHV9lChoBmgJaA9DCBtivObVKGNAlIaUUpRoFU3oA2gWR0CbRtOWSlnAdX2UKGgGaAloD0MID4C4q1ddY0CUhpRSlGgVTegDaBZHQJtVJyo4uK51fZQoaAZoCWgPQwiRgNHlzRdjQJSGlFKUaBVN6ANoFkdAm1UhFuvU0HV9lChoBmgJaA9DCMDQI0bPgmJAlIaUUpRoFU3oA2gWR0CbZEVsDW9UdX2UKGgGaAloD0MIxLEubiOwYkCUhpRSlGgVTegDaBZHQJtkP2K2rn11fZQoaAZoCWgPQwjpRe1+FSBiQJSGlFKUaBVN6ANoFkdAm4ocVclgMXV9lChoBmgJaA9DCO5cGOnF32FAlIaUUpRoFU3oA2gWR0CbihZElVtGdX2UKGgGaAloD0MI4stEEVIRY0CUhpRSlGgVTegDaBZHQJuXN00WM0h1fZQoaAZoCWgPQwgXDRmP0sdhQJSGlFKUaBVN6ANoFkdAm5cxOpKjBXV9lChoBmgJaA9DCNz10hQBu2FAlIaUUpRoFU3oA2gWR0CbomQtz0YkdX2UKGgGaAloD0MIpOL/jqgUY0CUhpRSlGgVTegDaBZHQJuiXiDM/yJ1fZQoaAZoCWgPQwi5bHTOzytjQJSGlFKUaBVN6ANoFkdAm642Af+0gXV9lChoBmgJaA9DCHRAEvZt7WFAlIaUUpRoFU3oA2gWR0Cbri/zreImdX2UKGgGaAloD0MIZ/FiYQiVYkCUhpRSlGgVTegDaBZHQJu5zR1HOKR1fZQoaAZoCWgPQwjtSPWdX3JjQJSGlFKUaBVN6ANoFkdAm7nHDaXa8HV9lChoBmgJaA9DCGISLuSR2mJAlIaUUpRoFU3oA2gWR0CbxWmZ3LV4dX2UKGgGaAloD0MItvKS/0kXYkCUhpRSlGgVTegDaBZHQJvFY4LkS291fZQoaAZoCWgPQwjoL/SIUfhhQJSGlFKUaBVN6ANoFkdAm9CkxdpqRHV9lChoBmgJaA9DCLtiRnj7EmNAlIaUUpRoFU3oA2gWR0Cb0J65Gz8hdX2UKGgGaAloD0MIGRwlr87xYUCUhpRSlGgVTegDaBZHQJveTiuMdcV1fZQoaAZoCWgPQwhZUu4+R+JhQJSGlFKUaBVN6ANoFkdAm95IFNcnmnV9lChoBmgJaA9DCM3OoneqfWJAlIaUUpRoFU3oA2gWR0Cb7FYF7laKdX2UKGgGaAloD0MImzi53yExY0CUhpRSlGgVTegDaBZHQJvsT/Pw/gR1fZQoaAZoCWgPQwiDFDyF3F9iQJSGlFKUaBVN6ANoFkdAm/pZOnEVFnV9lChoBmgJaA9DCN3NUx3yEWJAlIaUUpRoFU3oA2gWR0Cb+lMqSX+mdX2UKGgGaAloD0MIlbn5RnQoYkCUhpRSlGgVTegDaBZHQJwIihsZYPp1fZQoaAZoCWgPQwj9g0iGHENjQJSGlFKUaBVN6ANoFkdAnAiECaJAMXV9lChoBmgJaA9DCIRhwJIrKWJAlIaUUpRoFU3oA2gWR0CcFs/qgRK6dX2UKGgGaAloD0MIY9AJoQNGYkCUhpRSlGgVTegDaBZHQJwWydjG1hN1fZQoaAZoCWgPQwhY/+cwX1FjQJSGlFKUaBVN6ANoFkdAnDyDZtelbnV9lChoBmgJaA9DCK2kFd9QIWNAlIaUUpRoFU3oA2gWR0CcPH1aGHpKdX2UKGgGaAloD0MINA9gkd9sYkCUhpRSlGgVTegDaBZHQJxKiwLVnVZ1fZQoaAZoCWgPQwgFhxdEpOFhQJSGlFKUaBVN6ANoFkdAnEqE74i5eHV9lChoBmgJaA9DCM5sV+gDu2FAlIaUUpRoFU3oA2gWR0CcWKHM2WIHdX2UKGgGaAloD0MIzPEKRM8OYkCUhpRSlGgVTegDaBZHQJxYm7SRbKR1fZQoaAZoCWgPQwg4FD5bh/1iQJSGlFKUaBVN6ANoFkdAnGbOh9LHuXV9lChoBmgJaA9DCPpH36TpHmNAlIaUUpRoFU3oA2gWR0CcZshxHXmOdX2UKGgGaAloD0MIAtaqXZPLYkCUhpRSlGgVTegDaBZHQJx0y6WgOBl1fZQoaAZoCWgPQwi4zr9d9h1iQJSGlFKUaBVN6ANoFkdAnHTFlPJq7HV9lChoBmgJaA9DCAADQYAM52JAlIaUUpRoFU3oA2gWR0Ccgs3solUqdX2UKGgGaAloD0MIrDsW26QnY0CUhpRSlGgVTegDaBZHQJyCx+vyLAJ1fZQoaAZoCWgPQwi6FFeVfS5jQJSGlFKUaBVN6ANoFkdAnJCtupCKJnV9lChoBmgJaA9DCP1nzY8/7GFAlIaUUpRoFU3oA2gWR0CckKerdWQwdX2UKGgGaAloD0MI0QfL2FB2YUCUhpRSlGgVTegDaBZHQJyd7fhuO0d1fZQoaAZoCWgPQwhxjjo6LmFiQJSGlFKUaBVN6ANoFkdAnJ3n36AOKHV9lChoBmgJaA9DCMAhVKlZ3mJAlIaUUpRoFU3oA2gWR0Ccq78gpz91dX2UKGgGaAloD0MIxCRcyCNiYkCUhpRSlGgVTegDaBZHQJyruQ0XP7h1fZQoaAZoCWgPQwgWaHdIMf9iQJSGlFKUaBVN6ANoFkdAnLlwAp8WsXV9lChoBmgJaA9DCJAUkWGViWJAlIaUUpRoFU3oA2gWR0CcuWn5zo2XdX2UKGgGaAloD0MIA3egTnlYY0CUhpRSlGgVTegDaBZHQJzHa4RVZLZ1fZQoaAZoCWgPQwjThVj9EQViQJSGlFKUaBVN6ANoFkdAnMdla8pTdnV9lChoBmgJaA9DCBgIAmRoCmJAlIaUUpRoFU3oA2gWR0Cc1d4JeE7GdX2UKGgGaAloD0MIGm7A5wc4YkCUhpRSlGgVTegDaBZHQJzV1/MGHHp1fZQoaAZoCWgPQwj0MorlFuNhQJSGlFKUaBVN6ANoFkdAnOQgeV9nb3V9lChoBmgJaA9DCMDqyJFODGJAlIaUUpRoFU3oA2gWR0Cc5Bp+c6NmdWUu"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 489,
+    "n_steps": 1024,
+    "gamma": 0.9999,
+    "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-Swimmer-v3/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad83c149d4eb5cd9c0286d767186254bbdc083524c558aaa191cbf9f40232fc6
+size 43439

trpo-Swimmer-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8afa3459443ac39254ace50bbd67e0539bf82993c9f3a71a16437e990d36990
+size 43134

trpo-Swimmer-v3/pytorch_variables.pth

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

trpo-Swimmer-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:f8860b01f8800bf472522c3cfae90cfd08e629841634694836dbf4af80ed3417
+size 4379