Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Exploration

TL;DR

This paper introduces EMC, a novel multi-agent reinforcement learning method that uses curiosity-driven exploration based on prediction errors of individual Q-values, enhancing coordinated exploration and outperforming existing methods in complex tasks.

Contribution

The paper proposes a new intrinsic reward mechanism using individual Q-value prediction errors and episodic memory to improve exploration in multi-agent reinforcement learning.

Findings

EMC outperforms state-of-the-art MARL baselines in StarCraft II benchmarks.

Intrinsic rewards based on Q-value prediction errors promote coordinated exploration.

Episodic memory boosts policy training efficiency and effectiveness.

Abstract

Efficient exploration in deep cooperative multi-agent reinforcement learning (MARL) still remains challenging in complex coordination problems. In this paper, we introduce a novel Episodic Multi-agent reinforcement learning with Curiosity-driven exploration, called EMC. We leverage an insight of popular factorized MARL algorithms that the "induced" individual Q-values, i.e., the individual utility functions used for local execution, are the embeddings of local action-observation histories, and can capture the interaction between agents due to reward backpropagation during centralized training. Therefore, we use prediction errors of individual Q-values as intrinsic rewards for coordinated exploration and utilize episodic memory to exploit explored informative experience to boost policy training. As the dynamics of an agent's individual Q-value function captures the novelty of states and the influence from other agents, our intrinsic reward can induce coordinated exploration to new or promising states. We illustrate the advantages of our method by didactic examples, and demonstrate its significant outperformance over state-of-the-art MARL baselines on challenging tasks in the StarCraft II micromanagement benchmark.