Atari-specific utilities including Atari-specific network architectures.
This includes a class implementing minimal Atari 2600 preprocessing, which is in charge of: . Emitting a terminal signal when losing a life (optional). . Frame skipping and color pooling. . Resizing the image before it is provided to the agent.
class AtariPreprocessing: A class
implementing image preprocessing for Atari 2600 agents.
create_atari_environment(...):
Wraps an Atari 2600 Gym environment with some basic preprocessing.
implicit_quantile_network(...):
The Implicit Quantile ConvNet.
nature_dqn_network(...): The
convolutional network used to compute the agent's Q-values.
rainbow_network(...): The convolutional
network used to compute agent's Q-value distributions.