d3rlpy.datasets.get_atari¶

d3rlpy.datasets.get_atari(env_name, num_stack=None, sticky_action=True, pre_stack=False, render_mode=None)[source]¶

Returns atari dataset and envrironment.

The dataset is provided through d4rl-atari. See more details including available dataset from its GitHub page.

from d3rlpy.datasets import get_atari

dataset, env = get_atari('breakout-mixed-v0')

References

Parameters:

env_name (str) – environment id of d4rl-atari dataset.
num_stack (Optional[int]) – the number of frames to stack (only applied to env).
sticky_action (bool) – Flag to enable sticky action.
pre_stack (bool) – Flag to pre-stack observations. If this is False, FrameStackTransitionPicker and FrameStackTrajectorySlicer will be used to stack observations at sampling-time.
render_mode (Optional[str]) – Mode of rendering (human, rgb_array).

Returns:

tuple of d3rlpy.dataset.ReplayBuffer and gym environment.

Return type: