Initial commit

.gitattributes

@@ -33,3 +33,4 @@ 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 +1,94 @@
+---
+library_name: stable-baselines3
+tags:
+- seals/Hopper-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: seals/Hopper-v1
+      type: seals/Hopper-v1
+    metrics:
+    - type: mean_reward
+      value: 203.45 +/- 1.19
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **seals/Hopper-v1**
+This is a trained model of a **PPO** agent playing **seals/Hopper-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 ppo --env seals/Hopper-v1 -orga HumanCompatibleAI -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env seals/Hopper-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 ppo --env seals/Hopper-v1 -orga HumanCompatibleAI -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env seals/Hopper-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo ppo --env seals/Hopper-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo ppo --env seals/Hopper-v1 -f logs/ -orga HumanCompatibleAI
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 512),
+             ('clip_range', 0.1),
+             ('ent_coef', 0.0010159833764878474),
+             ('gae_lambda', 0.98),
+             ('gamma', 0.995),
+             ('learning_rate', 0.0003904770450788824),
+             ('max_grad_norm', 0.9),
+             ('n_envs', 1),
+             ('n_epochs', 20),
+             ('n_steps', 2048),
+             ('n_timesteps', 1000000.0),
+             ('normalize',
+              {'gamma': 0.995, 'norm_obs': False, 'norm_reward': True}),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs',
+              {'activation_fn': <class 'torch.nn.modules.activation.ReLU'>,
+               'features_extractor_class': <class 'imitation.policies.base.NormalizeFeaturesExtractor'>,
+               'net_arch': [{'pi': [64, 64], 'vf': [64, 64]}]}),
+             ('vf_coef', 0.20315938606555833),
+             ('normalize_kwargs',
+              {'norm_obs': {'gamma': 0.995,
+                            'norm_obs': False,
+                            'norm_reward': True},
+               'norm_reward': False})])
+```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

args.yml

@@ -0,0 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - conf_file
+    - hyperparams/python/ppo.py
+  - - device
+    - cpu
+  - - env
+    - seals/Hopper-v1
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 0
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - - seals
+  - - hyperparams
+    - null
+  - - log_folder
+    - gymnasium_models
+  - - 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
+    - 4
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 2774125859
+  - - 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
+  - - wandb_tags
+    - []

config.yml

@@ -0,0 +1,41 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 512
+  - - clip_range
+    - 0.1
+  - - ent_coef
+    - 0.0010159833764878474
+  - - gae_lambda
+    - 0.98
+  - - gamma
+    - 0.995
+  - - learning_rate
+    - 0.0003904770450788824
+  - - max_grad_norm
+    - 0.9
+  - - n_envs
+    - 1
+  - - n_epochs
+    - 20
+  - - n_steps
+    - 2048
+  - - n_timesteps
+    - 1000000.0
+  - - normalize
+    - gamma: 0.995
+      norm_obs: false
+      norm_reward: true
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - activation_fn: !!python/name:torch.nn.modules.activation.ReLU ''
+      features_extractor_class: !!python/name:imitation.policies.base.NormalizeFeaturesExtractor ''
+      net_arch:
+      - pi:
+        - 64
+        - 64
+        vf:
+        - 64
+        - 64
+  - - vf_coef
+    - 0.20315938606555833

env_kwargs.yml

@@ -0,0 +1 @@
+render_mode: rgb_array

ppo-seals-Hopper-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3a956ec98cd6dfbb0879dfa3bb378709851c5b3cf7f81b8019d1a000075e112
+size 152217

ppo-seals-Hopper-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+2.2.0a3

ppo-seals-Hopper-v1/data

@@ -0,0 +1,123 @@
+{
+    "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 0x7f9fe98ebee0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9fe98ebf70>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9fe9870040>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9fe98700d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f9fe9870160>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f9fe98701f0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f9fe9870280>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9fe9870310>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f9fe98703a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9fe9870430>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9fe98704c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9fe9870550>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f9fe98e8d50>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVuQAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARSZUxVlJOUjAhuZXRfYXJjaJR9lCiMAnBplF2UKEtAS0BljAJ2ZpRdlChLQEtAZXWMGGZlYXR1cmVzX2V4dHJhY3Rvcl9jbGFzc5SMF2ltaXRhdGlvbi5wb2xpY2llcy5iYXNllIwaTm9ybWFsaXplRmVhdHVyZXNFeHRyYWN0b3KUk5R1Lg==",
+        "activation_fn": "<class 'torch.nn.modules.activation.ReLU'>",
+        "net_arch": {
+            "pi": [
+                64,
+                64
+            ],
+            "vf": [
+                64,
+                64
+            ]
+        },
+        "features_extractor_class": "<class 'imitation.policies.base.NormalizeFeaturesExtractor'>"
+    },
+    "num_timesteps": 12168,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1694770544526030192,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV1QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZgAAAAAAAAAFALphsSbW6/qD/ve9YI9D8AQnOiR67rPr6dW5QQCWm/wFlSrwdyI78ivmch/J5jP9xupBaHQlK/7uOtfAJea78AGuFx6uXlPlQXlyecPmu/BBGuZvyFXT8O+z79w+9uP5SMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsMhpSMAUOUdJRSlC4="
+    },
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.98976,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 100,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float64",
+        "bounded_below": "[False False False False False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False False False False False]",
+        "_shape": [
+            12
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf inf inf inf inf]",
+        "low_repr": "-inf",
+        "high_repr": "inf",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True]",
+        "bounded_above": "[ True  True  True]",
+        "_shape": [
+            3
+        ],
+        "low": "[-1. -1. -1.]",
+        "high": "[1. 1. 1.]",
+        "low_repr": "-1.0",
+        "high_repr": "1.0",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
+    "n_steps": 2048,
+    "gamma": 0.995,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.0010159833764878474,
+    "vf_coef": 0.20315938606555833,
+    "max_grad_norm": 0.9,
+    "batch_size": 512,
+    "n_epochs": 20,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWVnQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMay9ob21lL20vRG9jdW1lbnRzL0NIQUkvcmwtYmFzZWxpbmVzMy16b28vdmVudi9saWIvcHl0aG9uMy44L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLg0MCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flGgMdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoHn2UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHPzmXHiNxn8uFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
+    }
+}

ppo-seals-Hopper-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdc18b91649c6959fbddf3457f66216828cad26adc7e1b7a2b090cde8e4648a1
+size 91888

ppo-seals-Hopper-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1f8ff9867d0595393f1cffacb658262cc1570475c72fb2472ac28a833848bf0
+size 46965

ppo-seals-Hopper-v1/pytorch_variables.pth

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

ppo-seals-Hopper-v1/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.4.0-156-generic-x86_64-with-glibc2.29 # 173-Ubuntu SMP Tue Jul 11 07:25:22 UTC 2023
+- Python: 3.8.10
+- Stable-Baselines3: 2.2.0a3
+- PyTorch: 2.0.1+cu117
+- GPU Enabled: False
+- Numpy: 1.24.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.21.0

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da0221d806c36e5f1ed0b439ea74df0b6e0d6e310e505bce03d462dd73c2af73
+size 365933

results.json

@@ -0,0 +1 @@
+{"mean_reward": 203.4494419, "std_reward": 1.193664113598336, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-19T11:45:17.447644"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:310c1fc359e13f83cf334aa5aadfad931b78c89798702d27dd511104b78be7cb
+size 515

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb1accfc07767c5925bb13ba61ff9729a3f5d999357530a3a400b4d7a47643f7
+size 1793