An Improved Multi-Agent Algorithm for Cooperative and Competitive Environments by Identifying and Encouraging Cooperation among Agents

TL;DR

This paper introduces an enhanced multi-agent reinforcement learning algorithm that promotes cooperation among agents, leading to improved team and individual rewards in competitive and cooperative settings.

Contribution

The paper presents a novel modification to MADDPG by adding a parameter to reward cooperative behavior, improving performance in multi-agent environments.

Findings

Higher team rewards achieved

Increased individual rewards

Better cooperation among agents

Abstract

We propose an improved algorithm by identifying and encouraging cooperative behavior in multi-agent environments. First, we analyze the shortcomings of existing algorithms in addressing multi-agent reinforcement learning problems. Then, based on the existing algorithm MADDPG, we introduce a new parameter to increase the reward that an agent can obtain when cooperative behavior among agents is identified. Finally, we compare our improved algorithm with MADDPG in environments from PettingZoo. The results show that the new algorithm helps agents achieve both higher team rewards and individual rewards.