Multiplayer Support for the Arcade Learning Environment

Abstract

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.

References in corpus (10)

• Playing Atari with Deep Reinforcement Learning
• Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
• Distributed Prioritized Experience Replay
• Rainbow: Combining Improvements in Deep Reinforcement Learning
• The Hanabi Challenge: A New Frontier for AI Research
• Go-Explore: a New Approach for Hard-Exploration Problems
• PettingZoo: Gym for Multi-Agent Reinforcement Learning
• OpenSpiel: A Framework for Reinforcement Learning in Games
• Revisiting Parameter Sharing in Multi-Agent Deep Reinforcement Learning
• SuperSuit: Simple Microwrappers for Reinforcement Learning Environments

Cited by in corpus (3)

• PettingZoo: Gym for Multi-Agent Reinforcement Learning
• A Game-Theoretic Approach to Multi-Agent Trust Region Optimization
• A coevolutionary approach to deep multi-agent reinforcement learning