arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2009.09341cs.LGcs.AI
收藏

支持多人游戏的街机学习环境

Multiplayer Support for the Arcade Learning Environment

Swarm Labs;University of Maryland, College Park(马里兰大学学院市分校)

J. K. Terry, Benjamin Black, Luis Santos

摘要:

Arcade Learning Environment(ALE)是强化学习社区中广泛使用的库,它允许通过Stella模拟器与Atari 2600游戏轻松编程接口。我们引入了一个公开可用的扩展ALE,扩展其支持多人游戏和游戏模式。这个界面还与PettingZoo集成,允许Python中的简单Gym-like界面与这些游戏交互。我们还为所有环境引入了实验基线。

英文摘要:

The Arcade Learning Environment ("ALE") is a widely used library in the reinforcement learning community that allows easy programmatic interfacing with Atari 2600 games, via the Stella emulator. We introduce a publicly available extension to the ALE that extends its support to multiplayer games and game modes. This interface is additionally integrated with PettingZoo to allow for a simple Gym-like interface in Python to interact with these games. We additionally introduce experimental baselines for all environments included.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑