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:
+- PandaSlide-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TQC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: PandaSlide-v3
+      type: PandaSlide-v3
+    metrics:
+    - type: mean_reward
+      value: -10.00 +/- 2.14
+      name: mean_reward
+      verified: false
+---
+
+# **TQC** Agent playing **PandaSlide-v3**
+This is a trained model of a **TQC** agent playing **PandaSlide-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 PandaSlide-v3 -orga chencliu -f logs/
+python -m rl_zoo3.enjoy --algo tqc --env PandaSlide-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 PandaSlide-v3 -orga chencliu -f logs/
+python -m rl_zoo3.enjoy --algo tqc --env PandaSlide-v3  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo tqc --env PandaSlide-v3 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo tqc --env PandaSlide-v3 -f logs/ -orga chencliu
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 2048),
+             ('buffer_size', 1000000),
+             ('ent_coef', 'auto'),
+             ('gamma', 0.95),
+             ('learning_rate', 0.001),
+             ('learning_starts', 100),
+             ('n_timesteps', 3000000.0),
+             ('normalize', True),
+             ('policy', 'MultiInputPolicy'),
+             ('policy_kwargs', 'dict(net_arch=[512, 512, 512], n_critics=2)'),
+             ('replay_buffer_class', 'HerReplayBuffer'),
+             ('replay_buffer_kwargs',
+              "dict( goal_selection_strategy='future', n_sampled_goal=4 )"),
+             ('tau', 0.05),
+             ('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
+    - PandaSlide-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
+    - 1526934768
+  - - 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 +1,27 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 2048
+  - - buffer_size
+    - 1000000
+  - - ent_coef
+    - auto
+  - - gamma
+    - 0.95
+  - - learning_rate
+    - 0.001
+  - - learning_starts
+    - 100
+  - - n_timesteps
+    - 3000000.0
+  - - normalize
+    - true
+  - - policy
+    - MultiInputPolicy
+  - - policy_kwargs
+    - dict(net_arch=[512, 512, 512], n_critics=2)
+  - - replay_buffer_class
+    - HerReplayBuffer
+  - - replay_buffer_kwargs
+    - dict( goal_selection_strategy='future', n_sampled_goal=4 )
+  - - tau
+    - 0.05

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 sha256:249008839b5227f0f4362ffde1a599ab4068d4a9588159bd4310aefbde18b966
+size 1036267

results.json

@@ -0,0 +1 @@
+{"mean_reward": -10.0, "std_reward": 2.1447610589527217, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-06T11:28:32.117778"}

tqc-PandaSlide-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3855837fca2fcc6107945dd156f4a6df9f514969e57b67107ac0f7476b0fe075
+size 24230586

tqc-PandaSlide-v3/_stable_baselines3_version

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

tqc-PandaSlide-v3/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bddf3797506628660c3a273fdd3a087e33171a3ba4bf6333933f4364dc74e1e7
+size 4337611

tqc-PandaSlide-v3/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:864b53c4f091cdb4e1f98214dd1c7b57340d40f9bd45c470b76f9ccc80bff81f
+size 8852565

tqc-PandaSlide-v3/data

@@ -0,0 +1,127 @@
+{
+    "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 0x7fc1ecebb880>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fc1eced5c40>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            512,
+            512,
+            512
+        ],
+        "n_critics": 2,
+        "use_sde": false
+    },
+    "num_timesteps": 3000000,
+    "_total_timesteps": 3000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1696495545839147064,
+    "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:": "gAWVWwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAAQ2nZvRzmvjyoS7I8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAAAIEFP7t7ub2PwvU8lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWSAAAAAAAAABp6ZE8E0C7PIRWLT5D6FS/jfFYP+IThL9Dadm9HOa+PKhLsjwAAAAAAAAAgAAAAAAAAAAAAAAAAKG3yL4AAAAAAAAAAAAAAACUaA5LAUsShpRoEnSUUpR1Lg==",
+        "achieved_goal": "[[-0.1061578   0.02330308  0.02176459]]",
+        "desired_goal": "[[ 0.52149963 -0.09056803  0.03      ]]",
+        "observation": "[[ 0.01781149  0.0228577   0.16927534 -0.83166903  0.8474358  -1.0318568\n  -0.1061578   0.02330308  0.02176459  0.         -0.          0.\n   0.          0.         -0.39202598  0.          0.          0.        ]]"
+    },
+    "_episode_num": 192717,
+    "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:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiJiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhlLg=="
+    },
+    "_n_updates": 2999900,
+    "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, (18,), 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": 2048,
+    "learning_starts": 100,
+    "tau": 0.05,
+    "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 0x7fc1ed239fc0>",
+        "__getstate__": "<function HerReplayBuffer.__getstate__ at 0x7fc1ed23a050>",
+        "__setstate__": "<function HerReplayBuffer.__setstate__ at 0x7fc1ed23a0e0>",
+        "set_env": "<function HerReplayBuffer.set_env at 0x7fc1ed23a170>",
+        "add": "<function HerReplayBuffer.add at 0x7fc1ed23a200>",
+        "_compute_episode_length": "<function HerReplayBuffer._compute_episode_length at 0x7fc1ed23a290>",
+        "sample": "<function HerReplayBuffer.sample at 0x7fc1ed23a320>",
+        "_get_real_samples": "<function HerReplayBuffer._get_real_samples at 0x7fc1ed23a3b0>",
+        "_get_virtual_samples": "<function HerReplayBuffer._get_virtual_samples at 0x7fc1ed23a440>",
+        "_sample_goals": "<function HerReplayBuffer._sample_goals at 0x7fc1ed23a4d0>",
+        "truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x7fc1ed23a560>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fc1ed24c600>"
+    },
+    "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:": "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"
+    },
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": []
+}

tqc-PandaSlide-v3/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c39898be0aa1ab7c4a85b43eb68348b5b1568a9e3f5dfe539d244432cbc10d9a
+size 1507

tqc-PandaSlide-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0faa2f1adf24299b17ffe25a3338f8ce4a17df8249e49ac00892165ff566ea34
+size 11019239

tqc-PandaSlide-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2565825362771099dc080f0c60e76bc3e6e65dfbb300c291f890999e7b75cd71
+size 747

tqc-PandaSlide-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 sha256:8039fc5a45cb28b1ebcc2425e7404faff9fbeb7aad47f2aff73f0e73f32efafe
+size 5324665

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da8b31a7649a32ab2bab28c13d94259dc693db390717573ff5b69613d848d367
+size 3082