- T
d4rl_adroit_hammer
- tensorflow.org
Updated May 8, 2024
Share
Facebook
Twitter
EmailClick to copy linkLink copiedCite(2024). d4rl_adroit_hammer [Dataset]. https://www.tensorflow.org/datasets/catalog/d4rl_adroit_hammerDataset updatedMay 8, 2024DescriptionD4RL is an open-source benchmark for offline reinforcement learning. It provides standardized environments and datasets for training and benchmarking algorithms.
The datasets follow the RLDS format to represent steps and episodes.
To use this dataset:
import tensorflow_datasets as tfds ds = tfds.load('d4rl_adroit_hammer', split='train') for ex in ds.take(4): print(ex)See the guide for more informations on tensorflow_datasets.
- T
d4rl_adroit_pen
- tensorflow.org
Updated May 8, 2024ShareFacebookTwitterEmailClick to copy linkLink copiedCite(2024). d4rl_adroit_pen [Dataset]. https://www.tensorflow.org/datasets/catalog/d4rl_adroit_penDataset updatedMay 8, 2024DescriptionD4RL is an open-source benchmark for offline reinforcement learning. It provides standardized environments and datasets for training and benchmarking algorithms.
The datasets follow the RLDS format to represent steps and episodes.
To use this dataset:
import tensorflow_datasets as tfds ds = tfds.load('d4rl_adroit_pen', split='train') for ex in ds.take(4): print(ex)See the guide for more informations on tensorflow_datasets.
- T
d4rl_antmaze
- tensorflow.org
Updated May 8, 2024ShareFacebookTwitterEmailClick to copy linkLink copiedCite(2024). d4rl_antmaze [Dataset]. https://www.tensorflow.org/datasets/catalog/d4rl_antmazeDataset updatedMay 8, 2024DescriptionD4RL is an open-source benchmark for offline reinforcement learning. It provides standardized environments and datasets for training and benchmarking algorithms.
The datasets follow the RLDS format to represent steps and episodes.
To use this dataset:
import tensorflow_datasets as tfds ds = tfds.load('d4rl_antmaze', split='train') for ex in ds.take(4): print(ex)See the guide for more informations on tensorflow_datasets.
- T
d4rl_adroit_door
- tensorflow.org
Updated May 8, 2024ShareFacebookTwitterEmailClick to copy linkLink copiedCite(2024). d4rl_adroit_door [Dataset]. https://www.tensorflow.org/datasets/catalog/d4rl_adroit_doorDataset updatedMay 8, 2024DescriptionD4RL is an open-source benchmark for offline reinforcement learning. It provides standardized environments and datasets for training and benchmarking algorithms.
The datasets follow the RLDS format to represent steps and episodes.
To use this dataset:
import tensorflow_datasets as tfds ds = tfds.load('d4rl_adroit_door', split='train') for ex in ds.take(4): print(ex)See the guide for more informations on tensorflow_datasets.
- T
d4rl_adroit_relocate
- tensorflow.org
Updated May 8, 2024ShareFacebookTwitterEmailClick to copy linkLink copiedCite(2024). d4rl_adroit_relocate [Dataset]. https://www.tensorflow.org/datasets/catalog/d4rl_adroit_relocateDataset updatedMay 8, 2024DescriptionD4RL is an open-source benchmark for offline reinforcement learning. It provides standardized environments and datasets for training and benchmarking algorithms.
The datasets follow the RLDS format to represent steps and episodes.
To use this dataset:
import tensorflow_datasets as tfds ds = tfds.load('d4rl_adroit_relocate', split='train') for ex in ds.take(4): print(ex)See the guide for more informations on tensorflow_datasets.
- T
d4rl_mujoco_hopper
- tensorflow.org
Updated May 8, 2024ShareFacebookTwitterEmailClick to copy linkLink copiedCite(2024). d4rl_mujoco_hopper [Dataset]. https://www.tensorflow.org/datasets/catalog/d4rl_mujoco_hopperDataset updatedMay 8, 2024DescriptionD4RL is an open-source benchmark for offline reinforcement learning. It provides standardized environments and datasets for training and benchmarking algorithms.
The datasets follow the RLDS format to represent steps and episodes.
To use this dataset:
import tensorflow_datasets as tfds ds = tfds.load('d4rl_mujoco_hopper', split='train') for ex in ds.take(4): print(ex)See the guide for more informations on tensorflow_datasets.
- T
d4rl_mujoco_walker2d
- tensorflow.org
Updated May 15, 2024ShareFacebookTwitterEmailClick to copy linkLink copiedCite(2024). d4rl_mujoco_walker2d [Dataset]. https://www.tensorflow.org/datasets/catalog/d4rl_mujoco_walker2dDataset updatedMay 15, 2024DescriptionD4RL is an open-source benchmark for offline reinforcement learning. It provides standardized environments and datasets for training and benchmarking algorithms.
The datasets follow the RLDS format to represent steps and episodes.
To use this dataset:
import tensorflow_datasets as tfds ds = tfds.load('d4rl_mujoco_walker2d', split='train') for ex in ds.take(4): print(ex)See the guide for more informations on tensorflow_datasets.
- T
d4rl_mujoco_halfcheetah
- tensorflow.org
Updated May 8, 2024ShareFacebookTwitterEmailClick to copy linkLink copiedCite(2024). d4rl_mujoco_halfcheetah [Dataset]. https://www.tensorflow.org/datasets/catalog/d4rl_mujoco_halfcheetahDataset updatedMay 8, 2024DescriptionD4RL is an open-source benchmark for offline reinforcement learning. It provides standardized environments and datasets for training and benchmarking algorithms.
The datasets follow the RLDS format to represent steps and episodes.
To use this dataset:
import tensorflow_datasets as tfds ds = tfds.load('d4rl_mujoco_halfcheetah', split='train') for ex in ds.take(4): print(ex)See the guide for more informations on tensorflow_datasets.
Not seeing a result you expected?
Learn how you can add new datasets to our index.
FacebookTwitterEmailD4RL is an open-source benchmark for offline reinforcement learning. It provides standardized environments and datasets for training and benchmarking algorithms.
The datasets follow the RLDS format to represent steps and episodes.
To use this dataset:
import tensorflow_datasets as tfds
ds = tfds.load('d4rl_adroit_hammer', split='train')
for ex in ds.take(4):
print(ex)
See the guide for more informations on tensorflow_datasets.