LLM-Mediated Guidance of MARL Systems

2025-03-16 · Philipp D. Siedler, Ian Gemp

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.

📄 PDF Abstract BibTeX arXiv:2503.13553

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language ModelMulti-agent Reinforcement Learning

A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning

2025-10-20 · Anjie Liu, Jianhong Wang, Samuel Kaski, Jun Wang 외 arxiv

Steering cooperative multi-agent reinforcement learning (MARL) towards desired outcomes is challenging, particularly when the global guidance from a human on the whole multi-agent system is impractical in a large-scale M…

Multi-agent Reinforcement Learning Causal Inference

Dynamic Reinsurance Treaty Bidding via Multi-Agent Reinforcement Learning

2025-06-16 · Stella C. Dong, James R. Finlay

This paper develops a novel multi-agent reinforcement learning (MARL) framework for reinsurance treaty bidding, addressing long-standing inefficiencies in traditional broker-mediated placement processes. We pose the core…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning

The Illusion of Opting in AI-Mediated Consequential Decisions

2026-05-27 · Eugene Yu Ji arxiv

Drawing on Ullmann-Margalit's concept of opting (transformative, irrevocable, and shadowed by foreclosed alternatives), we show that current AI systems raise a profound ethical problem that existing AI ethics has not ful…

Prioritized Guidance for Efficient Multi-Agent Reinforcement Learning Exploration

2019-07-18 · Qisheng Wang, Qichao Wang

Exploration efficiency is a challenging problem in multi-agent reinforcement learning (MARL), as the policy learned by confederate MARL depends on the collaborative approach among multiple agents. Another important probl…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Designing Human-mediated AI Guidance: Ready Together for Personalized Family Emergency Preparedness

2026-08-20 · Nini Kurashvili, Yana Ivanchenko, Greta Schiavo, Cansu Koyuturk 외 arxiv

Artificial intelligence (AI) systems are increasingly used across domains to provide personalized information, recommendations, and decision support. However, in some contexts, AI-generated information may not be suitabl…