Credit Assignment and Efficient Exploration based on Influence Scope in Multi-agent Reinforcement Learning

TL;DR

This paper presents a novel multi-agent reinforcement learning method that improves credit assignment and exploration in sparse-reward environments by calculating the influence scope of agents on states, leading to significant performance gains.

Contribution

The paper introduces the Influence Scope of Agents (ISA) algorithm, which enhances credit assignment and exploration by quantifying agents' influence on state attributes in sparse-reward MARL.

Findings

ISA significantly outperforms baseline methods in various scenarios.

The method effectively improves credit assignment accuracy.

Enhanced exploration leads to better policy learning.

Abstract

Training cooperative agents in sparse-reward scenarios poses significant challenges for multi-agent reinforcement learning (MARL). Without clear feedback on actions at each step in sparse-reward setting, previous methods struggle with precise credit assignment among agents and effective exploration. In this paper, we introduce a novel method to deal with both credit assignment and exploration problems in reward-sparse domains. Accordingly, we propose an algorithm that calculates the Influence Scope of Agents (ISA) on states by taking specific value of the dimensions/attributes of states that can be influenced by individual agents. The mutual dependence between agents' actions and state attributes are then used to calculate the credit assignment and to delimit the exploration space for each individual agent. We then evaluate ISA in a variety of sparse-reward multi-agent scenarios. The results show that our method significantly outperforms the state-of-art baselines.