LLM-Mediated Guidance of MARL Systems
This work addresses the problem of improving training efficiency and performance in MARL systems for researchers and practitioners, though it appears incremental as it builds on existing MARL and LLM methods.
This paper tackles the challenge of achieving efficient learning and desirable behaviors in complex multi-agent environments by combining Multi-Agent Reinforcement Learning (MARL) with Large Language Model (LLM)-mediated interventions to guide agents. The results show that agents benefit from early interventions, with both Natural Language and Rule-Based Controllers outperforming a baseline without interventions, leading to more efficient training and higher performance.
In complex multi-agent environments, achieving efficient learning and desirable behaviours is a significant challenge for Multi-Agent Reinforcement Learning (MARL) systems. This work explores the potential of combining MARL with Large Language Model (LLM)-mediated interventions to guide agents toward more desirable behaviours. Specifically, we investigate how LLMs can be used to interpret and facilitate interventions that shape the learning trajectories of multiple agents. We experimented with two types of interventions, referred to as controllers: a Natural Language (NL) Controller and a Rule-Based (RB) Controller. The NL Controller, which uses an LLM to simulate human-like interventions, showed a stronger impact than the RB Controller. Our findings indicate that agents particularly benefit from early interventions, leading to more efficient training and higher performance. Both intervention types outperform the baseline without interventions, highlighting the potential of LLM-mediated guidance to accelerate training and enhance MARL performance in challenging environments.