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:
+- ReacherBulletEnv-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TD3
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 19.37 +/- 10.31
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: ReacherBulletEnv-v0
+      type: ReacherBulletEnv-v0
+---
+
+# **TD3** Agent playing **ReacherBulletEnv-v0**
+This is a trained model of a **TD3** agent playing **ReacherBulletEnv-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 ReacherBulletEnv-v0 -orga sb3 -f logs/
+python enjoy.py --algo td3 --env ReacherBulletEnv-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo td3 --env ReacherBulletEnv-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo td3 --env ReacherBulletEnv-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', 300000.0),
+             ('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
+    - ReacherBulletEnv-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
+    - 4011578699
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - 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
+    - 300000.0
+  - - 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 sha256:87b5df07d1171f87f01243543bf56e2cefd1787d28200e8bad5ee67b51ce1db2
+size 64472

results.json

@@ -0,0 +1 @@
+{"mean_reward": 19.3729623, "std_reward": 10.309905917134348, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T15:06:42.988097"}

td3-ReacherBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d6ab580a4413e10df36c03dedbdb089b6a357a2a8adf3ffeb2f4d63f74fd32a
+size 6072012

td3-ReacherBulletEnv-v0/_stable_baselines3_version

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

td3-ReacherBulletEnv-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a82d0d8f217e04fd2de9d3442c4978f047eaff557e8bbee49e83968366daecb4
+size 1005761

td3-ReacherBulletEnv-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52cd08588959b3ebd08fba429829e11b291d74666e6910896bd2b10fce5f63bc
+size 2019229

td3-ReacherBulletEnv-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 0x7f1397df5170>",
+        "_build": "<function TD3Policy._build at 0x7f1397df5200>",
+        "_get_constructor_parameters": "<function TD3Policy._get_constructor_parameters at 0x7f1397df5290>",
+        "make_actor": "<function TD3Policy.make_actor at 0x7f1397df5320>",
+        "make_critic": "<function TD3Policy.make_critic at 0x7f1397df53b0>",
+        "forward": "<function TD3Policy.forward at 0x7f1397df5440>",
+        "_predict": "<function TD3Policy._predict at 0x7f1397df54d0>",
+        "set_training_mode": "<function TD3Policy.set_training_mode at 0x7f1397df5560>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f1397df21e0>"
+    },
+    "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   0.]",
+        "high": "[inf inf inf inf inf inf inf inf inf  1.]",
+        "bounded_below": "[False False False False False False False False False  True]",
+        "bounded_above": "[False False False False False False False False False  True]",
+        "_np_random": null,
+        "_shape": [
+            10
+        ]
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "low": "[-1. -1.]",
+        "high": "[1. 1.]",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_np_random": "RandomState(MT19937)",
+        "_shape": [
+            2
+        ]
+    },
+    "n_envs": 1,
+    "num_timesteps": 300000,
+    "_total_timesteps": 300000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": {
+        ":type:": "<class 'stable_baselines3.common.noise.NormalActionNoise'>",
+        ":serialized:": "gASVFAEAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5ub2lzZZSMEU5vcm1hbEFjdGlvbk5vaXNllJOUKYGUfZQojANfbXWUjBVudW1weS5jb3JlLm11bHRpYXJyYXmUjAxfcmVjb25zdHJ1Y3SUk5SMBW51bXB5lIwHbmRhcnJheZSTlEsAhZRDAWKUh5RSlChLAUsChZRoCYwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKJQxAAAAAAAAAAAAAAAAAAAAAAlHSUYowGX3NpZ21hlGgIaAtLAIWUaA2HlFKUKEsBSwKFlGgViUMQmpmZmZmZuT+amZmZmZm5P5R0lGJ1Yi4=",
+        "_mu": "[0. 0.]",
+        "_sigma": "[0.1 0.1]"
+    },
+    "start_time": 1614940762.297999,
+    "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:": "gASVsgAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLCoaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUMofKifPela8b2L20s8txkIvclKkr7gU3U/xaIsvQ4Swb74FhA+DnTaO5R0lGIu"
+    },
+    "_episode_num": 2000,
+    "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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 290100,
+    "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 0x7f1398272b90>",
+        "add": "<function ReplayBuffer.add at 0x7f1398272c20>",
+        "sample": "<function ReplayBuffer.sample at 0x7f1397dd97a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f1397dd9830>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f13982c95d0>"
+    },
+    "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-ReacherBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29ce76567317d8987b8e212f2a4547d6b72c531332af2cfab0ff7456e209b7a8
+size 3027321

td3-ReacherBulletEnv-v0/pytorch_variables.pth

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

td3-ReacherBulletEnv-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 sha256:4345d3ed3428c2b1510366b95a81f3db542b34bf374291e130f5a79d32d3882c
+size 58403