Abstract We introduce CuLE (CUDA Learning Environment), a CUDA port of the Atari
Learning Environment (ALE) which is used for the development of deep reinforcement …

Deep reinforcement learning (RL) has achieved many recent successes, yet experiment turn-
around time remains a key bottleneck in research and in practice. We investigate how to …

We propose Pgx, a suite of board game reinforcement learning (RL) environments written in
JAX and optimized for GPU/TPU accelerators. By leveraging JAX's auto-vectorization and …

Achieving efficient and scalable exploration in complex domains poses a major challenge in
reinforcement learning. While Bayesian and PAC-MDP approaches to the exploration …

Much human and computational effort has aimed to improve how deep reinforcement
learning algorithms perform on benchmarks such as the Atari Learning Environment …

Consistent and reproducible evaluation of Deep Reinforcement Learning (DRL) is not
straightforward. In the Arcade Learning Environment (ALE), small changes in environment …

Recent reinforcement learning (RL) approaches have shown strong performance in complex
domains such as Atari games, but are often highly sample inefficient. A common approach to …

Reinforcement learning is a wide ranging subfield of machine learning, which has been
brought to the forefront of research after the unprecedented rise of deep learning. The …

We propose a novel framework for efficient parallelization of deep reinforcement learning
algorithms, enabling these algorithms to learn from multiple actors on a single machine. The …

WarpDrive is a flexible, lightweight, and easy-to-use open-source framework for end-to-end
deep multi-agent reinforcement learning (MARL) on a Graphics Processing Unit (GPU) …