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 +1,84 @@
+---
+library_name: stable-baselines3
+tags:
+- PandaReach-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TQC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: PandaReach-v3
+      type: PandaReach-v3
+    metrics:
+    - type: mean_reward
+      value: -2.00 +/- 0.77
+      name: mean_reward
+      verified: false
+---
+
+# **TQC** Agent playing **PandaReach-v3**
+This is a trained model of a **TQC** agent playing **PandaReach-v3**
+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 PandaReach-v3 -orga chencliu -f logs/
+python -m rl_zoo3.enjoy --algo tqc --env PandaReach-v3  -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 PandaReach-v3 -orga chencliu -f logs/
+python -m rl_zoo3.enjoy --algo tqc --env PandaReach-v3  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo tqc --env PandaReach-v3 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo tqc --env PandaReach-v3 -f logs/ -orga chencliu
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 256),
+             ('buffer_size', 1000000),
+             ('ent_coef', 'auto'),
+             ('gamma', 0.95),
+             ('learning_rate', 0.001),
+             ('learning_starts', 1000),
+             ('n_timesteps', 20000.0),
+             ('normalize', True),
+             ('policy', 'MultiInputPolicy'),
+             ('policy_kwargs', 'dict(net_arch=[64, 64], n_critics=1)'),
+             ('replay_buffer_class', 'HerReplayBuffer'),
+             ('replay_buffer_kwargs',
+              "dict( goal_selection_strategy='future', n_sampled_goal=4 )"),
+             ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
+```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

args.yml

@@ -0,0 +1,83 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - tqc
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - PandaReach-v3
+  - - env_kwargs
+    - null
+  - - eval_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
+    - 60077985
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - track
+    - false
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - sb3
+  - - wandb_tags
+    - []

config.yml

@@ -0,0 +1,25 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 256
+  - - buffer_size
+    - 1000000
+  - - ent_coef
+    - auto
+  - - gamma
+    - 0.95
+  - - learning_rate
+    - 0.001
+  - - learning_starts
+    - 1000
+  - - n_timesteps
+    - 20000.0
+  - - normalize
+    - true
+  - - policy
+    - MultiInputPolicy
+  - - policy_kwargs
+    - dict(net_arch=[64, 64], n_critics=1)
+  - - replay_buffer_class
+    - HerReplayBuffer
+  - - replay_buffer_kwargs
+    - dict( goal_selection_strategy='future', n_sampled_goal=4 )

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 sha256:6bff981af17c438f4117ee01f3e06b2b1207c0d824cc6f32123060241d7f9b34
+size 667356

results.json

@@ -0,0 +1 @@
+{"mean_reward": -2.0, "std_reward": 0.7745966692414834, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-03T16:38:14.219553"}

tqc-PandaReach-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e55336fbc4e0ced8e6d3f38e883007c2fd057f018816bc4d4494b5813cd00fef
+size 212990

tqc-PandaReach-v3/_stable_baselines3_version

@@ -0,0 +1 @@
+2.1.0

tqc-PandaReach-v3/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1193b180ad69e6f9d79f77e67a8e6baacead55b77a01a2297c408c36c8d7253b
+size 49565

tqc-PandaReach-v3/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80fb23c6d493cc70f66da2f52c8bac19301384564d494ae40e610434a7281a66
+size 59439

tqc-PandaReach-v3/data

@@ -0,0 +1,126 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVMQAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu",
+        "__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 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 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 MultiInputPolicy.__init__ at 0x7fe5ef4eb880>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fe5ef505140>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            64,
+            64
+        ],
+        "n_critics": 1,
+        "use_sde": false
+    },
+    "num_timesteps": 20000,
+    "_total_timesteps": 20000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1696320824737719967,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'collections.OrderedDict'>",
+        ":serialized:": "gAWVKwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAA6nIdPRlsGqxDI0o+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAA570FPu7vMr3jT0U+lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWGAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAACUaA5LAUsGhpRoEnSUUpR1Lg==",
+        "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]]",
+        "desired_goal": "[[ 0.13060723 -0.04368585  0.19268756]]",
+        "observation": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]]"
+    },
+    "_episode_num": 4859,
+    "use_sde": false,
+    "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:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhlLg=="
+    },
+    "_n_updates": 19000,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.dict.Dict'>",
+        ":serialized:": "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",
+        "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])",
+        "_shape": null,
+        "dtype": null,
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True]",
+        "bounded_above": "[ True  True  True]",
+        "_shape": [
+            3
+        ],
+        "low": "[-1. -1. -1.]",
+        "high": "[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": 1000,
+    "tau": 0.005,
+    "gamma": 0.95,
+    "gradient_steps": 1,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVPwAAAAAAAACMJ3N0YWJsZV9iYXNlbGluZXMzLmhlci5oZXJfcmVwbGF5X2J1ZmZlcpSMD0hlclJlcGxheUJ1ZmZlcpSTlC4=",
+        "__module__": "stable_baselines3.her.her_replay_buffer",
+        "__doc__": "\n    Hindsight Experience Replay (HER) buffer.\n    Paper: https://arxiv.org/abs/1707.01495\n\n    Replay buffer for sampling HER (Hindsight Experience Replay) transitions.\n\n    .. note::\n\n      Compared to other implementations, the ``future`` goal sampling strategy is inclusive:\n      the current transition can be used when re-sampling.\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 env: The training environment\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        Disabled for now (see https://github.com/DLR-RM/stable-baselines3/pull/243#discussion_r531535702)\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    :param n_sampled_goal: Number of virtual transitions to create per real transition,\n        by sampling new goals.\n    :param goal_selection_strategy: Strategy for sampling goals for replay.\n        One of ['episode', 'final', 'future']\n    :param copy_info_dict: Whether to copy the info dictionary and pass it to\n        ``compute_reward()`` method.\n        Please note that the copy may cause a slowdown.\n        False by default.\n    ",
+        "__init__": "<function HerReplayBuffer.__init__ at 0x7fe5efa5dfc0>",
+        "__getstate__": "<function HerReplayBuffer.__getstate__ at 0x7fe5efa5e050>",
+        "__setstate__": "<function HerReplayBuffer.__setstate__ at 0x7fe5efa5e0e0>",
+        "set_env": "<function HerReplayBuffer.set_env at 0x7fe5efa5e170>",
+        "add": "<function HerReplayBuffer.add at 0x7fe5efa5e200>",
+        "_compute_episode_length": "<function HerReplayBuffer._compute_episode_length at 0x7fe5efa5e290>",
+        "sample": "<function HerReplayBuffer.sample at 0x7fe5efa5e320>",
+        "_get_real_samples": "<function HerReplayBuffer._get_real_samples at 0x7fe5efa5e3b0>",
+        "_get_virtual_samples": "<function HerReplayBuffer._get_virtual_samples at 0x7fe5efa5e440>",
+        "_sample_goals": "<function HerReplayBuffer._sample_goals at 0x7fe5efa5e4d0>",
+        "truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x7fe5efa5e560>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fe5efa63a80>"
+    },
+    "replay_buffer_kwargs": {
+        "goal_selection_strategy": "future",
+        "n_sampled_goal": 4
+    },
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -3.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "top_quantiles_to_drop_per_net": 2,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWV7wIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMXi9ob21lL2xjYy9hbmFjb25kYTMvZW52cy9ybF96b28vbGliL3B5dGhvbjMuMTAvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuDQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjF4vaG9tZS9sY2MvYW5hY29uZGEzL2VudnMvcmxfem9vL2xpYi9weXRob24zLjEwL3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz9QYk3S8an8hZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
+    },
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": []
+}

tqc-PandaReach-v3/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f555dcf5477059ad10e18e782ccb572b9c1ef0eba704f80be2a8d157ae6a64b3
+size 1507

tqc-PandaReach-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fc2c3d36f2f71fa12bfd49509a1a7895387c27d70591ea3771eef365ed62ae0
+size 83177

tqc-PandaReach-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c96643b64fd79d0fd7e42695ba0df2960e2042290c3def2ed0a39c9058ad7386
+size 747

tqc-PandaReach-v3/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.0-84-generic-x86_64-with-glibc2.31 # 93~20.04.1-Ubuntu SMP Wed Sep 6 16:15:40 UTC 2023
+- Python: 3.10.0
+- Stable-Baselines3: 2.1.0
+- PyTorch: 2.0.1+cu117
+- GPU Enabled: True
+- Numpy: 1.25.2
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.26.2

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a2f39aab6f66546c3a0f46afab5c6c2fa822c1e08d9d39d1b6a28a4e2af0352
+size 113647

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd8b431486ee0bbb9d77167c98ef8e4ebd8f1dfd39907563bdc42c739e16766b
+size 2722