Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms

Understand

Recent years have witnessed significant advances in reinforcement learning (RL), which has registered great success in solving various sequential decision-making problems in machine learning.

• Most of the successful RL applications, e.g., the games of Go and Poker, robotics, and autonomous driving, involve the participation of more than one single agent, which naturally fall into the realm of multi-agent RL (MARL), a domain with a relatively long history, and has recently re-emerged due to advances in single-agent RL techniques.
• Though empirically successful, theoretical foundations for MARL are relatively lacking in the literature.
• In this chapter, we provide a selective overview of MARL, with focus on algorithms backed by theoretical analysis.