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:
+- AntBulletEnv-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TD3
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: AntBulletEnv-v0
+      type: AntBulletEnv-v0
+    metrics:
+    - type: mean_reward
+      value: 3204.34 +/- 882.86
+      name: mean_reward
+      verified: false
+---
+
+# **TD3** Agent playing **AntBulletEnv-v0**
+This is a trained model of a **TD3** agent playing **AntBulletEnv-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 td3 --env AntBulletEnv-v0 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo td3 --env AntBulletEnv-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 td3 --env AntBulletEnv-v0 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo td3 --env AntBulletEnv-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo td3 --env AntBulletEnv-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo td3 --env AntBulletEnv-v0 -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', 1000000.0),
+             ('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
+    - td3
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - AntBulletEnv-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
+    - 2082379321
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/AntBulletEnv-v0__td3__2082379321__1672160310
+  - - 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
+    - 1000000.0
+  - - noise_std
+    - 0.1
+  - - noise_type
+    - normal
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(net_arch=[400, 300])
+  - - train_freq
+    - - 1
+      - episode

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cafbef1d13acee711eb0d2ad5397efac8aeae078560886ede7c2a277331a0c5
+size 1282205

results.json

@@ -0,0 +1 @@
+{"mean_reward": 3204.34303, "std_reward": 882.860279070717, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T16:27:07.166475"}

td3-AntBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81b4696b74eaaef24edc486734158ba9250119ef7fc2b84382ab7df18078fe42
+size 6529058

td3-AntBulletEnv-v0/_stable_baselines3_version

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

td3-AntBulletEnv-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06cb78e747b40b3e0891c05f25e65724bd460c58d7e480b1615a6a06b5974e48
+size 1079343

td3-AntBulletEnv-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61e9e2cf0b48db9667d82d4bf6b115a6f9863a503ef2ab17556179a3fe03f4e1
+size 2175801

td3-AntBulletEnv-v0/data

@@ -0,0 +1,126 @@
+{
+    "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 0x7f1785a6e940>",
+        "_build": "<function TD3Policy._build at 0x7f1785a6e9d0>",
+        "_get_constructor_parameters": "<function TD3Policy._get_constructor_parameters at 0x7f1785a6ea60>",
+        "make_actor": "<function TD3Policy.make_actor at 0x7f1785a6eaf0>",
+        "make_critic": "<function TD3Policy.make_critic at 0x7f1785a6eb80>",
+        "forward": "<function TD3Policy.forward at 0x7f1785a6ec10>",
+        "_predict": "<function TD3Policy._predict at 0x7f1785a6eca0>",
+        "set_training_mode": "<function TD3Policy.set_training_mode at 0x7f1785a6ed30>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f1785a71a00>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            400,
+            300
+        ]
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            28
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -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 inf inf inf inf inf inf\n 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 False False False False False False False False False\n False False False False]",
+        "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            8
+        ],
+        "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]",
+        "high": "[1. 1. 1. 1. 1. 1. 1. 1.]",
+        "bounded_below": "[ True  True  True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True  True  True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 1000051,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": {
+        ":type:": "<class 'stable_baselines3.common.noise.NormalActionNoise'>",
+        ":serialized:": "gAWVWgEAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5ub2lzZZSMEU5vcm1hbEFjdGlvbk5vaXNllJOUKYGUfZQojANfbXWUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwGX3NpZ21hlGgIKJZAAAAAAAAAAJqZmZmZmbk/mpmZmZmZuT+amZmZmZm5P5qZmZmZmbk/mpmZmZmZuT+amZmZmZm5P5qZmZmZmbk/mpmZmZmZuT+UaA9LCIWUaBN0lFKUdWIu",
+        "_mu": "[0. 0. 0. 0. 0. 0. 0. 0.]",
+        "_sigma": "[0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1]"
+    },
+    "start_time": 1672160312802386131,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWVvQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMRS9ob21lL3FnYWxsb3VlZGVjL3N0YWJsZS1iYXNlbGluZXMzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMRS9ob21lL3FnYWxsb3VlZGVjL3N0YWJsZS1iYXNlbGluZXMzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/UGJN0vGp/IWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
+    },
+    "tensorboard_log": "runs/AntBulletEnv-v0__td3__2082379321__1672160310/AntBulletEnv-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:": "gAWV5QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZwAAAAAAAAAI1iVL4LDUo+kfd6Pwj+hT9Q4kE9A2uVvg9WJT3FYFm+bncWP5t6cj4w85U+RmNkPyVU7T1KZXi/FIBvPyvADD72no8+QK5Ov6Ycaj+rf30+5+uuPNN0Kb5QO5C+5NBDvwAAAAAAAAAAAACAPwAAAACUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLHIaUjAFDlHSUUpQu"
+    },
+    "_episode_num": 1012,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -5.100000000002325e-05,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 990588,
+    "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 0x7f1785a6a430>",
+        "add": "<function ReplayBuffer.add at 0x7f1785a6a4c0>",
+        "sample": "<function ReplayBuffer.sample at 0x7f1785a6a550>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f1785a6a5e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f1785ef1f80>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVZAAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMB2VwaXNvZGWUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "policy_delay": 2,
+    "target_noise_clip": 0.5,
+    "target_policy_noise": 0.2,
+    "actor_batch_norm_stats": [],
+    "critic_batch_norm_stats": [],
+    "actor_batch_norm_stats_target": [],
+    "critic_batch_norm_stats_target": []
+}

td3-AntBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7513cc185b31f3874d7e484e3f5fe70c0913478bcb097c613e2e8e216030886
+size 3252921

td3-AntBulletEnv-v0/pytorch_variables.pth

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

td3-AntBulletEnv-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

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba36dc31d6abe70004968e95d49c7802422c8f14c64c5f7601f94200cb07504f
+size 34200