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 +1,70 @@
+---
+library_name: stable-baselines3
+tags:
+- MountainCarContinuous-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: DDPG
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: MountainCarContinuous-v0
+      type: MountainCarContinuous-v0
+    metrics:
+    - type: mean_reward
+      value: 93.72 +/- 0.13
+      name: mean_reward
+      verified: false
+---
+
+# **DDPG** Agent playing **MountainCarContinuous-v0**
+This is a trained model of a **DDPG** agent playing **MountainCarContinuous-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
+
+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 MountainCarContinuous-v0 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo ddpg --env MountainCarContinuous-v0  -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 MountainCarContinuous-v0 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo ddpg --env MountainCarContinuous-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo ddpg --env MountainCarContinuous-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo ddpg --env MountainCarContinuous-v0 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('n_timesteps', 300000),
+             ('noise_std', 0.5),
+             ('noise_type', 'ornstein-uhlenbeck'),
+             ('policy', 'MlpPolicy'),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ddpg
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - MountainCarContinuous-v0
+  - - 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
+    - 4280148352
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/MountainCarContinuous-v0__ddpg__4280148352__1671826538
+  - - 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 +1,9 @@
+!!python/object/apply:collections.OrderedDict
+- - - n_timesteps
+    - 300000
+  - - noise_std
+    - 0.5
+  - - noise_type
+    - ornstein-uhlenbeck
+  - - policy
+    - MlpPolicy

ddpg-MountainCarContinuous-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84b5711bd349523c9a26fea1885358a97f180197a94a216c7783d387bf2ddad3
+size 3940595

ddpg-MountainCarContinuous-v0/_stable_baselines3_version

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

ddpg-MountainCarContinuous-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:941581c612074e808afe96c2a250ca3fa34369d3237c5d3dfd59f470a2fba0af
+size 979247

ddpg-MountainCarContinuous-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d440d1eaec6b56d22fad05dcc824b8142938289ebb96f22966b2959d21eeb4ce
+size 982447

ddpg-MountainCarContinuous-v0/data

@@ -0,0 +1,132 @@
+{
+    "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 0x7f3292bad940>",
+        "_build": "<function TD3Policy._build at 0x7f3292bad9d0>",
+        "_get_constructor_parameters": "<function TD3Policy._get_constructor_parameters at 0x7f3292bada60>",
+        "make_actor": "<function TD3Policy.make_actor at 0x7f3292badaf0>",
+        "make_critic": "<function TD3Policy.make_critic at 0x7f3292badb80>",
+        "forward": "<function TD3Policy.forward at 0x7f3292badc10>",
+        "_predict": "<function TD3Policy._predict at 0x7f3292badca0>",
+        "set_training_mode": "<function TD3Policy.set_training_mode at 0x7f3292badd30>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f3292bb1840>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "n_critics": 1
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWVYwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAACamZm/KVyPvZRoCksChZSMAUOUdJRSlIwEaGlnaJRoEiiWCAAAAAAAAACamRk/KVyPPZRoCksChZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolgIAAAAAAAAAAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYCAAAAAAAAAAEBlGghSwKFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu",
+        "dtype": "float32",
+        "_shape": [
+            2
+        ],
+        "low": "[-1.2  -0.07]",
+        "high": "[0.6  0.07]",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            1
+        ],
+        "low": "[-1.]",
+        "high": "[1.]",
+        "bounded_below": "[ True]",
+        "bounded_above": "[ True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 300032,
+    "_total_timesteps": 300000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": {
+        ":type:": "<class 'stable_baselines3.common.noise.OrnsteinUhlenbeckActionNoise'>",
+        ":serialized:": "gAWVVQEAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5ub2lzZZSMHE9ybnN0ZWluVWhsZW5iZWNrQWN0aW9uTm9pc2WUk5QpgZR9lCiMBl90aGV0YZRHP8MzMzMzMzOMA19tdZSMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlIwGX3NpZ21hlGgJKJYIAAAAAAAAAAAAAAAAAOA/lGgQSwGFlGgUdJRSlIwDX2R0lEc/hHrhR64Ue4wNaW5pdGlhbF9ub2lzZZROjApub2lzZV9wcmV2lGgJKJYIAAAAAAAAAAAAAAAAAAAAlGgQSwGFlGgUdJRSlHViLg==",
+        "_theta": 0.15,
+        "_mu": "[0.]",
+        "_sigma": "[0.5]",
+        "_dt": 0.01,
+        "initial_noise": null,
+        "noise_prev": "[0.]"
+    },
+    "start_time": 1671826540769964459,
+    "learning_rate": 0.001,
+    "tensorboard_log": "runs/MountainCarContinuous-v0__ddpg__4280148352__1671826538/MountainCarContinuous-v0",
+    "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:": "gAWVfQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAENt4z6VCw89lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwKGlIwBQ5R0lFKULg=="
+    },
+    "_episode_num": 2994,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.00010666666666669933,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 300032,
+    "buffer_size": 1,
+    "batch_size": 100,
+    "learning_starts": 100,
+    "tau": 0.005,
+    "gamma": 0.99,
+    "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 0x7f3292baa430>",
+        "add": "<function ReplayBuffer.add at 0x7f3292baa4c0>",
+        "sample": "<function ReplayBuffer.sample at 0x7f3292baa550>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f3292baa5e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f3292ba1680>"
+    },
+    "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:": "gAWVeQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAgD+UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLAYaUjAFDlHSUUpQu"
+    }
+}

ddpg-MountainCarContinuous-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40de28ca55a0d95b83a4c52d2a812ae97ffaaf9a004f684eb64fb59cf463132b
+size 1959965

ddpg-MountainCarContinuous-v0/pytorch_variables.pth

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

ddpg-MountainCarContinuous-v0/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:c1582a3f6aad049d3f05165a43327a254334626eb575ecbc63b7d5a4a7695977
+size 270695

results.json

@@ -0,0 +1 @@
+{"mean_reward": 93.7224091, "std_reward": 0.12611714529630758, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T17:21:21.655975"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4411d4719e4ec315e7024f266f914149753a7b18997918644b7ecca210a29a65
+size 77292