Initial commit

.gitattributes

@@ -33,3 +33,4 @@ 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 +1,85 @@
+---
+library_name: stable-baselines3
+tags:
+- AntBulletEnv-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TQC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: AntBulletEnv-v0
+      type: AntBulletEnv-v0
+    metrics:
+    - type: mean_reward
+      value: 3483.69 +/- 16.40
+      name: mean_reward
+      verified: false
+---
+
+# **TQC** Agent playing **AntBulletEnv-v0**
+This is a trained model of a **TQC** 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 tqc --env AntBulletEnv-v0 -orga Emperor-WS -f logs/
+python -m rl_zoo3.enjoy --algo tqc --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 tqc --env AntBulletEnv-v0 -orga Emperor-WS -f logs/
+python -m rl_zoo3.enjoy --algo tqc --env AntBulletEnv-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo tqc --env AntBulletEnv-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo tqc --env AntBulletEnv-v0 -f logs/ -orga Emperor-WS
+```
+
+## 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', 1000000.0),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(log_std_init=-3, net_arch=[400, 300])'),
+             ('tau', 0.02),
+             ('train_freq', 64),
+             ('use_sde', True),
+             ('normalize', False)])
+```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

args.yml

@@ -0,0 +1,59 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - tqc
+  - - 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
+    - 2054332755
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - true
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,29 @@
+!!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
+    - 1000000.0
+  - - 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 @@
+render_mode: rgb_array

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccd60c5001eb8eaabd286cefa463f2b391333efa28cb5d8229cfc6c147cdc6e3
+size 1286334

results.json

@@ -0,0 +1 @@
+{"mean_reward": 3483.6901841999997, "std_reward": 16.395939155759937, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-01T01:23:53.982935"}

tqc-AntBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d73086b951ec6368e8a66600b8accccca9530bbd022dc41037d10247546071a9
+size 6268199

tqc-AntBulletEnv-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+2.3.0a2

tqc-AntBulletEnv-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e26366b41e9226c348569f7fa32a23a8f72ec3e52ce5ee2d8618dc49062ec35c
+size 1102807

tqc-AntBulletEnv-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cffbc7a334ef6336f9aa47f181384f02b6d0d22a822c09d1a698dde09de0b4ee
+size 2297578

tqc-AntBulletEnv-v0/data

@@ -0,0 +1,130 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVKgAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMCVRRQ1BvbGljeZSTlC4=",
+        "__module__": "sb3_contrib.tqc.policies",
+        "__annotations__": "{'actor': <class 'sb3_contrib.tqc.policies.Actor'>, 'critic': <class 'sb3_contrib.tqc.policies.Critic'>, 'critic_target': <class 'sb3_contrib.tqc.policies.Critic'>}",
+        "__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 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 0x7cdbcb477520>",
+        "_build": "<function TQCPolicy._build at 0x7cdbcb4775b0>",
+        "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7cdbcb477640>",
+        "reset_noise": "<function TQCPolicy.reset_noise at 0x7cdbcb4776d0>",
+        "make_actor": "<function TQCPolicy.make_actor at 0x7cdbcb477760>",
+        "make_critic": "<function TQCPolicy.make_critic at 0x7cdbcb4777f0>",
+        "forward": "<function TQCPolicy.forward at 0x7cdbcb477880>",
+        "_predict": "<function TQCPolicy._predict at 0x7cdbcb477910>",
+        "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7cdbcb4779a0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7cdbcb485f80>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "log_std_init": -3,
+        "net_arch": [
+            400,
+            300
+        ],
+        "use_sde": true
+    },
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1614621417.2337935,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_last_episode_starts": null,
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV6QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZ0AAAAAAAAAMfRO74Ffrm+2ptuPydWdz+REN29IfERvtcfX7013YS+H7jHPi30ar+jX4I+XVVBu3jsXr8YZ7M+L2I1PwksoT4Qnxu/TewbParQfj+ymk29Dr6Gvi5q0r7AqLE9rSpbPgAAAAAAAIA/AACAPwAAAABkO989lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSx2GlIwBQ5R0lFKULg=="
+    },
+    "_episode_num": 1013,
+    "use_sde": true,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.0,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 990016,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "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]",
+        "_shape": [
+            29
+        ],
+        "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.]",
+        "low_repr": "[-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_repr": "[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.]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True  True  True]",
+        "_shape": [
+            8
+        ],
+        "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]",
+        "high": "[1. 1. 1. 1. 1. 1. 1. 1.]",
+        "low_repr": "-1.0",
+        "high_repr": "1.0",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
+    "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:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
+        "__module__": "stable_baselines3.common.buffers",
+        "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}",
+        "__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 0x7cdbcc43a440>",
+        "add": "<function ReplayBuffer.add at 0x7cdbcc43a4d0>",
+        "sample": "<function ReplayBuffer.sample at 0x7cdbcc43a560>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7cdbcc43a5f0>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7cdbcc43a680>)>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7cdbcc5b4200>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLQGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -8.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "top_quantiles_to_drop_per_net": 2,
+    "_last_dones": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "remove_time_limit_termination": false,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS9vcHQvY29uZGEvbGliL3B5dGhvbjMuMTAvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuDQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvb3B0L2NvbmRhL2xpYi9weXRob24zLjEwL3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
+    },
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": []
+}

tqc-AntBulletEnv-v0/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c8aad7684158b298b218de556548afbdf3d1c0066598f09922726731b3eedbb
+size 1940

tqc-AntBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e84f5ae6b0bbc2403b2d027a7f65094681c6adba8a51c3ba6196921f00d6b3b1
+size 2846969

tqc-AntBulletEnv-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0a864c5c64ff9f5ff632ff09509e4d3bd9ece362756753d890003bb774ddab1
+size 1180

tqc-AntBulletEnv-v0/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.133+-x86_64-with-glibc2.31 # 1 SMP Tue Dec 19 13:14:11 UTC 2023
+- Python: 3.10.13
+- Stable-Baselines3: 2.3.0a2
+- PyTorch: 2.1.2+cpu
+- GPU Enabled: False
+- Numpy: 1.26.3
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.0
+- OpenAI Gym: 0.26.2

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a342a75e5b7df4acfc3cd1d01c1f108ae05798d7e9b4a36086a1371a1af14412
+size 48224