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 +1,68 @@
+---
+library_name: stable-baselines3
+tags:
+- ReacherBulletEnv-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TQC
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 20.27 +/- 10.54
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: ReacherBulletEnv-v0
+      type: ReacherBulletEnv-v0
+---
+
+# **TQC** Agent playing **ReacherBulletEnv-v0**
+This is a trained model of a **TQC** 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 tqc --env ReacherBulletEnv-v0 -orga sb3 -f logs/
+python enjoy.py --algo tqc --env ReacherBulletEnv-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo tqc --env ReacherBulletEnv-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo tqc --env ReacherBulletEnv-v0 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 256),
+             ('buffer_size', 300000),
+             ('ent_coef', 'auto'),
+             ('env_wrapper', 'sb3_contrib.common.wrappers.TimeFeatureWrapper'),
+             ('gamma', 0.98),
+             ('gradient_steps', 64),
+             ('learning_rate', 0.00073),
+             ('learning_starts', 10000),
+             ('n_timesteps', 300000.0),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(log_std_init=-3, net_arch=[400, 300])'),
+             ('tau', 0.02),
+             ('train_freq', 64),
+             ('use_sde', True),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,59 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - tqc
+  - - 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
+    - 3633192636
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,29 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 256
+  - - buffer_size
+    - 300000
+  - - ent_coef
+    - auto
+  - - env_wrapper
+    - sb3_contrib.common.wrappers.TimeFeatureWrapper
+  - - gamma
+    - 0.98
+  - - gradient_steps
+    - 64
+  - - learning_rate
+    - 0.00073
+  - - learning_starts
+    - 10000
+  - - n_timesteps
+    - 300000.0
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(log_std_init=-3, net_arch=[400, 300])
+  - - tau
+    - 0.02
+  - - train_freq
+    - 64
+  - - use_sde
+    - true

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec67991b6989b9a006abb2ec57c69bcc61ee81ae852e4cc6ebb735f7bb44aecc
+size 64074

results.json

@@ -0,0 +1 @@
+{"mean_reward": 20.272237500000003, "std_reward": 10.537794619295, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T20:56:13.318126"}

tqc-ReacherBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8834aedd771d6ab75f38e321063b2438cef823a4ed8a60616c3be28d366e0a3b
+size 5809750

tqc-ReacherBulletEnv-v0/_stable_baselines3_version

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

tqc-ReacherBulletEnv-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:223780de833843d22c57c919e00afadb2271eae0f0d9c09fae6a6640dbd3e85c
+size 1011003

tqc-ReacherBulletEnv-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f271091ae020d1f45f1eefcd3c7adb2ee1417f06e01905a96bdb7fee0137647a
+size 2134685

tqc-ReacherBulletEnv-v0/data

@@ -0,0 +1,123 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVKgAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMCVRRQ1BvbGljeZSTlC4=",
+        "__module__": "sb3_contrib.tqc.policies",
+        "__doc__": "\n    Policy class (with both actor and critic) for TQC.\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 use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the feature 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_quantiles: Number of quantiles for the critic.\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 TQCPolicy.__init__ at 0x7faf39c26710>",
+        "_build": "<function TQCPolicy._build at 0x7faf39c267a0>",
+        "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7faf39c26830>",
+        "reset_noise": "<function TQCPolicy.reset_noise at 0x7faf39c268c0>",
+        "make_actor": "<function TQCPolicy.make_actor at 0x7faf39c26950>",
+        "make_critic": "<function TQCPolicy.make_critic at 0x7faf39c269e0>",
+        "forward": "<function TQCPolicy.forward at 0x7faf39c26a70>",
+        "_predict": "<function TQCPolicy._predict at 0x7faf39c26b00>",
+        "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7faf39c26b90>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7faf39c86690>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "log_std_init": -3,
+        "net_arch": [
+            400,
+            300
+        ],
+        "use_sde": true
+    },
+    "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": 300032,
+    "_total_timesteps": 300000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1614940600.3107479,
+    "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/////0sAdJRiiUMoKVUdPg4Fq7zbhyw9sd6suhRlYz97Lus+8keNPNhgc75f2QS95RdLP5R0lGIu"
+    },
+    "_episode_num": 2000,
+    "use_sde": true,
+    "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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 290048,
+    "buffer_size": 1,
+    "batch_size": 256,
+    "learning_starts": 10000,
+    "tau": 0.02,
+    "gamma": 0.98,
+    "gradient_steps": 64,
+    "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 0x7faf3a400b90>",
+        "add": "<function ReplayBuffer.add at 0x7faf3a400c20>",
+        "sample": "<function ReplayBuffer.sample at 0x7faf39f677a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7faf39f67830>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7faf3a4575d0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gASVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLQGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -2.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "top_quantiles_to_drop_per_net": 2,
+    "_last_dones": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQCUdJRiLg=="
+    },
+    "remove_time_limit_termination": false
+}

tqc-ReacherBulletEnv-v0/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29abe3f370cdca1895d7f2c105e04961590adfbde3242b3dc9c85979f2de3c7c
+size 1255

tqc-ReacherBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18a36d639b8dd1b2d9abee8a6fefd2b8194c7c8bdc1f775d3572a2ec0929e7bb
+size 2642248

tqc-ReacherBulletEnv-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc8e0deb7f7aaddad30dc5de02f327e6a1f09a51836314503097b21bbabd6868
+size 747

tqc-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 sha256:8f2f09914b68e3a9c56fe5b1a5d45eee02987a21d7f39f3150ee0709b6db248c
+size 58528