d3rlpy.datasets.get_dataset

d3rlpy.datasets.get_dataset(env_name, create_mask=False, mask_size=1)

Returns dataset and envrironment by guessing from name.

This function returns dataset by matching name with the following datasets.

• cartpole-replay

• cartpole-random

• pendulum-replay

• pendulum-random

• d4rl-pybullet

• d4rl-atari

• d4rl

import d3rlpy

# cartpole dataset
dataset, env = d3rlpy.datasets.get_dataset('cartpole')

# pendulum dataset
dataset, env = d3rlpy.datasets.get_dataset('pendulum')

# d4rl-pybullet dataset
dataset, env = d3rlpy.datasets.get_dataset('hopper-bullet-mixed-v0')

# d4rl-atari dataset
dataset, env = d3rlpy.datasets.get_dataset('breakout-mixed-v0')

# d4rl dataset
dataset, env = d3rlpy.datasets.get_dataset('hopper-medium-v0')

Parameters

• env_name (str) – environment id of the dataset.

• create_mask (bool) – flag to create binary mask for bootstrapping.

• mask_size (int) – ensemble size for binary mask.

Returns

tuple of d3rlpy.dataset.MDPDataset and gym environment.

Return type

Tuple[d3rlpy.dataset.MDPDataset, gym.core.Env]