Recursive Reasoning Graph for Multi-Agent Reinforcement Learning
This addresses the challenge of agents accurately anticipating others' responses in MARL, which is crucial for effective cooperation or competition in multi-agent systems.
The paper tackles the problem of multi-agent reinforcement learning (MARL) in complex interaction scenarios by proposing the Recursive Reasoning Graph (R2G) algorithm, which achieves state-of-the-art performance on multiple multi-agent particle and robotics games.
Multi-agent reinforcement learning (MARL) provides an efficient way for simultaneously learning policies for multiple agents interacting with each other. However, in scenarios requiring complex interactions, existing algorithms can suffer from an inability to accurately anticipate the influence of self-actions on other agents. Incorporating an ability to reason about other agents' potential responses can allow an agent to formulate more effective strategies. This paper adopts a recursive reasoning model in a centralized-training-decentralized-execution framework to help learning agents better cooperate with or compete against others. The proposed algorithm, referred to as the Recursive Reasoning Graph (R2G), shows state-of-the-art performance on multiple multi-agent particle and robotics games.