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 +1,77 @@
+---
+library_name: stable-baselines3
+tags:
+- Pendulum-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: DDPG
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Pendulum-v1
+      type: Pendulum-v1
+    metrics:
+    - type: mean_reward
+      value: -186.96 +/- 111.06
+      name: mean_reward
+      verified: false
+---
+
+# **DDPG** Agent playing **Pendulum-v1**
+This is a trained model of a **DDPG** agent playing **Pendulum-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 ddpg --env Pendulum-v1 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo ddpg --env Pendulum-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 ddpg --env Pendulum-v1 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo ddpg --env Pendulum-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo ddpg --env Pendulum-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo ddpg --env Pendulum-v1 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('buffer_size', 200000),
+             ('gamma', 0.98),
+             ('gradient_steps', -1),
+             ('learning_rate', 0.001),
+             ('learning_starts', 10000),
+             ('n_timesteps', 20000),
+             ('noise_std', 0.1),
+             ('noise_type', 'normal'),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(net_arch=[400, 300])'),
+             ('train_freq', [1, 'episode']),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ddpg
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - Pendulum-v1
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - 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
+    - -1
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 2415310802
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/Pendulum-v1__ddpg__2415310802__1671827730
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - openrlbenchmark
+  - - wandb_project_name
+    - sb3
+  - - yaml_file
+    - null

config.yml

@@ -0,0 +1,24 @@
+!!python/object/apply:collections.OrderedDict
+- - - buffer_size
+    - 200000
+  - - gamma
+    - 0.98
+  - - gradient_steps
+    - -1
+  - - learning_rate
+    - 0.001
+  - - learning_starts
+    - 10000
+  - - n_timesteps
+    - 20000
+  - - noise_std
+    - 0.1
+  - - noise_type
+    - normal
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(net_arch=[400, 300])
+  - - train_freq
+    - - 1
+      - episode

ddpg-Pendulum-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:838c3e09b91e6d67a1560b475e7198d697cc18e18a62f3cc485ac461fd6d85cc
+size 3955648

ddpg-Pendulum-v1/_stable_baselines3_version

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

ddpg-Pendulum-v1/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:544ade46d8257d2ca8bc1d8695eac899bd7bcc80ffbebff18da97e53feb17551
+size 982447

ddpg-Pendulum-v1/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b7032fb6f63c7195b15ceda375173cea6cb12f1fe4ceabdd022541330c445db
+size 985647

ddpg-Pendulum-v1/data

@@ -0,0 +1,135 @@
+{
+    "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 0x7fac6f1ee940>",
+        "_build": "<function TD3Policy._build at 0x7fac6f1ee9d0>",
+        "_get_constructor_parameters": "<function TD3Policy._get_constructor_parameters at 0x7fac6f1eea60>",
+        "make_actor": "<function TD3Policy.make_actor at 0x7fac6f1eeaf0>",
+        "make_critic": "<function TD3Policy.make_critic at 0x7fac6f1eeb80>",
+        "forward": "<function TD3Policy.forward at 0x7fac6f1eec10>",
+        "_predict": "<function TD3Policy._predict at 0x7fac6f1eeca0>",
+        "set_training_mode": "<function TD3Policy.set_training_mode at 0x7fac6f1eed30>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fac6f1f4300>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            400,
+            300
+        ],
+        "n_critics": 1
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            3
+        ],
+        "low": "[-1. -1. -8.]",
+        "high": "[1. 1. 8.]",
+        "bounded_below": "[ True  True  True]",
+        "bounded_above": "[ True  True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            1
+        ],
+        "low": "[-2.]",
+        "high": "[2.]",
+        "bounded_below": "[ True]",
+        "bounded_above": "[ True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 20000,
+    "_total_timesteps": 20000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": {
+        ":type:": "<class 'stable_baselines3.common.noise.NormalActionNoise'>",
+        ":serialized:": "gAWV6gAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5ub2lzZZSMEU5vcm1hbEFjdGlvbk5vaXNllJOUKYGUfZQojANfbXWUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAYWUjAFDlHSUUpSMBl9zaWdtYZRoCCiWCAAAAAAAAACamZmZmZm5P5RoD0sBhZRoE3SUUpR1Yi4=",
+        "_mu": "[0.]",
+        "_sigma": "[0.1]"
+    },
+    "start_time": 1671827732798257385,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/Pendulum-v1__ddpg__2415310802__1671827730/Pendulum-v1",
+    "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:": "gAWVgQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYMAAAAAAAAAK37fz8rLTy8a2gUvpSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsDhpSMAUOUdJRSlC4="
+    },
+    "_episode_num": 100,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 10000,
+    "buffer_size": 1,
+    "batch_size": 100,
+    "learning_starts": 10000,
+    "tau": 0.005,
+    "gamma": 0.98,
+    "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 0x7fac6f1ea430>",
+        "add": "<function ReplayBuffer.add at 0x7fac6f1ea4c0>",
+        "sample": "<function ReplayBuffer.sample at 0x7fac6f1ea550>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fac6f1ea5e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fac6f1eb100>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVZAAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMB2VwaXNvZGWUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "policy_delay": 1,
+    "target_noise_clip": 0.0,
+    "target_policy_noise": 0.1,
+    "_action_repeat": [
+        null
+    ],
+    "surgeon": null,
+    "actor_batch_norm_stats": [],
+    "critic_batch_norm_stats": [],
+    "actor_batch_norm_stats_target": [],
+    "critic_batch_norm_stats_target": [],
+    "_last_action": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVeQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAEgI6j+UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLAYaUjAFDlHSUUpQu"
+    }
+}

ddpg-Pendulum-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaf2942c2c37375b8da1d77482c9c93b1ad5e5de53d550efa3ea2092889ca5dd
+size 1966365

ddpg-Pendulum-v1/pytorch_variables.pth

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

ddpg-Pendulum-v1/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

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2c4ef156504a461e6429090c46cd07e94a358b37e1e6ef11d264b5341cf4a11
+size 371049

results.json

@@ -0,0 +1 @@
+{"mean_reward": -186.9558699, "std_reward": 111.06011659058022, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T17:25:29.411904"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d12706544b9ffdf8d80cd0ac484fd6a90442c355a4a6cc50aa5ff2f1a9671c8e
+size 2841