Initial commit

.gitattributes

@@ -25,3 +25,4 @@ 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

README.md

@@ -0,0 +1,66 @@
+---
+library_name: stable-baselines3
+tags:
+- AntBulletEnv-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TD3
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 3262.99 +/- 64.99
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: AntBulletEnv-v0
+      type: AntBulletEnv-v0
+---
+
+# **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
+
+```
+# Download model and save it into the logs/ folder
+python -m utils.load_from_hub --algo td3 --env AntBulletEnv-v0 -orga sb3 -f logs/
+python enjoy.py --algo td3 --env AntBulletEnv-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo td3 --env AntBulletEnv-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo td3 --env AntBulletEnv-v0 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('buffer_size', 200000),
+             ('env_wrapper', 'sb3_contrib.common.wrappers.TimeFeatureWrapper'),
+             ('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 +1,59 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - td3
+  - - env
+    - AntBulletEnv-v0
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 10
+  - - eval_freq
+    - 10000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - rl-trained-agents/
+  - - log_interval
+    - -1
+  - - n_evaluations
+    - 20
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 10
+  - - num_threads
+    - -1
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 1635842902
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - true
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,26 @@
+!!python/object/apply:collections.OrderedDict
+- - - buffer_size
+    - 200000
+  - - env_wrapper
+    - sb3_contrib.common.wrappers.TimeFeatureWrapper
+  - - 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:cc6c487febb5fd9936d836decc5f40ca740acf8d29caacb1ce3acf6869251ebb
+size 1250998

results.json

@@ -0,0 +1 @@
+{"mean_reward": 3262.9855607, "std_reward": 64.9854329720947, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T15:03:59.006968"}

td3-AntBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:984998d301a08654d70cb961c679ebbd16b59e58947f3d703e36e8957305dc31
+size 6543702

td3-AntBulletEnv-v0/_stable_baselines3_version

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

td3-AntBulletEnv-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:617f2084a040e3c90abe1efef9e3af2fae6fb33d2dee3de3277292e16a3fde26
+size 1080961

td3-AntBulletEnv-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff4bca3ab4737007485a97bfa0b3117c9fae92387df37b2a8f6cfa5cba6e161f
+size 2179229

td3-AntBulletEnv-v0/data

@@ -0,0 +1,124 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnRkMy5wb2xpY2llc5SMCVREM1BvbGljeZSTlC4=",
+        "__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 0x7eff49be3170>",
+        "_build": "<function TD3Policy._build at 0x7eff49be3200>",
+        "_get_constructor_parameters": "<function TD3Policy._get_constructor_parameters at 0x7eff49be3290>",
+        "make_actor": "<function TD3Policy.make_actor at 0x7eff49be3320>",
+        "make_critic": "<function TD3Policy.make_critic at 0x7eff49be33b0>",
+        "forward": "<function TD3Policy.forward at 0x7eff49be3440>",
+        "_predict": "<function TD3Policy._predict at 0x7eff49be34d0>",
+        "set_training_mode": "<function TD3Policy.set_training_mode at 0x7eff49be3560>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7eff49bdf210>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            400,
+            300
+        ]
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "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\n   0.]",
+        "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  1.]",
+        "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  True]",
+        "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  True]",
+        "_np_random": null,
+        "_shape": [
+            29
+        ]
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "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)",
+        "_shape": [
+            8
+        ]
+    },
+    "n_envs": 1,
+    "num_timesteps": 1000054,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": {
+        ":type:": "<class 'stable_baselines3.common.noise.NormalActionNoise'>",
+        ":serialized:": "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",
+        "_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": 1614621305.74363,
+    "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": null,
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASV/gAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLHYaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUN0cjw+vlHwLT6fR3w/v/J1PwFQED1d0EA8d3H3PP1iT76h00I/5o7jPo7yJr8UaAS/FM7iPQWhWz9j7DQ/bAH1PqCtfz/q0Hk/fF0uP8NTg73mpkm/7DeGvhq5Rz4bWV0+AAAAAAAAgD8AAAAAAACAP28SgzqUdJRiLg=="
+    },
+    "_episode_num": 1057,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -5.3999999999998494e-05,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 990085,
+    "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:": "gASVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
+        "__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:\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    :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 0x7eff4a060b90>",
+        "add": "<function ReplayBuffer.add at 0x7eff4a060c20>",
+        "sample": "<function ReplayBuffer.sample at 0x7eff49bc77a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7eff49bc7830>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7eff4a0b75d0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gASVZAAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMB2VwaXNvZGWUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "policy_delay": 2,
+    "target_noise_clip": 0.5,
+    "target_policy_noise": 0.2,
+    "_last_dones": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQCUdJRiLg=="
+    },
+    "remove_time_limit_termination": false
+}

td3-AntBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32f527a04ba95b44469c60984608b3008da3f8e16255fb6abf42b8d15a0c44ff
+size 3262521

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-5.13.0-44-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

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4820cfab2fe19f8a4959308407424cdca6f220b350f34ee319eabbdf4f0d6338
+size 48660