Initial commit

.gitattributes

@@ -25,3 +25,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text
+vec_normalize.pkl filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,67 @@
+---
+library_name: stable-baselines3
+tags:
+- HopperBulletEnv-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TRPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 2650.38 +/- 63.62
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: HopperBulletEnv-v0
+      type: HopperBulletEnv-v0
+---
+
+# **TRPO** Agent playing **HopperBulletEnv-v0**
+This is a trained model of a **TRPO** agent playing **HopperBulletEnv-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
+
+```
+# Download model and save it into the logs/ folder
+python -m utils.load_from_hub --algo trpo --env HopperBulletEnv-v0 -orga sb3 -f logs/
+python enjoy.py --algo trpo --env HopperBulletEnv-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo trpo --env HopperBulletEnv-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo trpo --env HopperBulletEnv-v0 -f logs/ -orga sb3
+```
+
+## 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 +1,65 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - trpo
+  - - env
+    - HopperBulletEnv-v0
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 20
+  - - eval_freq
+    - 50000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - 10
+  - - n_eval_envs
+    - 10
+  - - n_evaluations
+    - 20
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 10
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - -1
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 22485597
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

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 sha256:2dec0f5129f7e4eaa5f1cb864040b4f0528de1008d76d186830cae0eb8d58fea
+size 1331377

results.json

@@ -0,0 +1 @@
+{"mean_reward": 2650.3779315, "std_reward": 63.61860545995893, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T13:02:26.652378"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6de153037430969bf23f54b2e8c7b0e838012c23a26213b975e57d3ff6e5f82f
+size 85925

trpo-HopperBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddde91fde385a1e08806b264bf44b6da8eb513c93d492ec19fb681eeda3823a3
+size 110932

trpo-HopperBulletEnv-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.1a8

trpo-HopperBulletEnv-v0/data

@@ -0,0 +1,102 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
+        "__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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7f06286bc950>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f06286bc9e0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f06286bca70>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f06286bcb00>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f06286bcb90>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f06286bcc20>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f06286bccb0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f06286bcd40>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f06286bcdd0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f06286bce60>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f06286bcef0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f062870d840>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gASVDwIAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMA2xvd5SMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlGgGjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSw+FlGgLiUM8AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/lHSUYowEaGlnaJRoEWgTSwCFlGgVh5RSlChLAUsPhZRoC4lDPAAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5R0lGKMDWJvdW5kZWRfYmVsb3eUaBFoE0sAhZRoFYeUUpQoSwFLD4WUaAiMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGKJQw8AAAAAAAAAAAAAAAAAAACUdJRijA1ib3VuZGVkX2Fib3ZllGgRaBNLAIWUaBWHlFKUKEsBSw+FlGgpiUMPAAAAAAAAAAAAAAAAAAAAlHSUYowKX25wX3JhbmRvbZROjAZfc2hhcGWUSw+FlHViLg==",
+        "dtype": "float32",
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf]",
+        "high": "[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]",
+        "bounded_above": "[False False False False False False False False False False False False\n False False False]",
+        "_np_random": null,
+        "_shape": [
+            15
+        ]
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "low": "[-1. -1. -1.]",
+        "high": "[1. 1. 1.]",
+        "bounded_below": "[ True  True  True]",
+        "bounded_above": "[ True  True  True]",
+        "_np_random": "RandomState(MT19937)",
+        "_shape": [
+            3
+        ]
+    },
+    "n_envs": 2,
+    "num_timesteps": 1001472,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1640773405.621584,
+    "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:": "gASVigAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwKFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAgAAlHSUYi4="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVAgEAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwJLD4aUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUN4AAAAAAAAAAAAAIA/AAAAAAAAAAAAAAAAAAAAAAAAAIAxH34/AAAAACeLhT8AAAAA82zFvQAAAAAAAAAAAAAAAAAAAAAAAIA/AAAAAAAAAAAAAAAAAAAAAAAAAIBYk4A/AAAAANJTgT8AAAAAoELxPQAAAAAAAAAAlHSUYi4="
+    },
+    "_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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_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-HopperBulletEnv-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f006a8a4155849506f868950f09805bd4fdc8eb07452b93b819cfdc20a0092f0
+size 45313

trpo-HopperBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9504f13fd4da5fc25db12adef9db6081d84ab69010cc9bde1c44aff1711f5238
+size 46846

trpo-HopperBulletEnv-v0/pytorch_variables.pth

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

trpo-HopperBulletEnv-v0/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.13.0-44-generic-x86_64-with-debian-bullseye-sid #49~20.04.1-Ubuntu SMP Wed May 18 18:44:28 UTC 2022
+Python: 3.7.10
+Stable-Baselines3: 1.5.1a8
+PyTorch: 1.11.0
+GPU Enabled: True
+Numpy: 1.21.2
+Gym: 0.21.0

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9588f930ad0bebce45159af4b8679a02ee15ecb57bad68088906a97bab805ad7
+size 4782