transparent value getter (auto unboxing)

Initialize the ALE class with a given environment Args: env_name (str): The name of the Atari rom num_envs (int): The

envs: list of gym environments to run in subprocesses

Sample initial states by taking random number of no-ops on reset. No-op is assumed to be action 0.

Take action on reset for environments that are fixed until firing.

Make end-of-life == end-of-episode, but only reset on true game over. Done by DeepMind for the DQN and co. since it helps value estimation.

Return only every `skip`-th frame

Stack k last frames. Returns lazy array, which is much more memory efficient. See Also -------- baselines.common.atari

This object ensures that common frames between the observations are only stored once. It exists purely to optimize memory usage which can be h

Bin reward to {+1, 0, -1} by its sign.

Compute the collision decode table

set the specified field to the lower `length` bits of (src>>shift)

Set ALE to evaluation mode

default ctor