paper-with-me

Papers

PIMAEX: Multi-Agent Exploration through Peer Incentivization

2025-01-02 · Michael Kölle, Johannes Tochtermann, Julian Schönberger, Gerhard Stenzel, Philipp Altmann, Claudia Linnhoff-Popien

While exploration in single-agent reinforcement learning has been studied extensively in recent years, considerably less work has focused on its counterpart in multi-agent reinforcement learning. To address this issue, this work proposes a peer-incentivized reward function inspired by previous research on intrinsic curiosity and influence-based rewards. The \textit{PIMAEX} reward, short for Peer-Incentivized Multi-Agent Exploration, aims to improve exploration in the multi-agent setting by encouraging agents to exert influence over each other to increase the likelihood of encountering novel states. We evaluate the \textit{PIMAEX} reward in conjunction with \textit{PIMAEX-Communication}, a multi-agent training algorithm that employs a communication channel for agents to influence one another. The evaluation is conducted in the \textit{Consume/Explore} environment, a partially observable environment with deceptive rewards, specifically designed to challenge the exploration vs.\ exploitation dilemma and the credit-assignment problem. The results empirically demonstrate that agents using the \textit{PIMAEX} reward with \textit{PIMAEX-Communication} outperform those that do not.

📄 PDF Abstract BibTeX arXiv:2501.01266

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learningreinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

Multi-Agent LLMs Fail to Explore Each Other

2026-07-13 · Hyeong Kyu Choi, Jiatong Li, Wendi Li, Xin Eric Wang 외 hf

Exploration is essential for reliable autonomy in multi-agent systems, yet it remains unclear whether large language model (LLM) agents can explore effectively when interacting with one another. We show that modern LLM a…

Fast Peer Adaptation with Context-aware Exploration

2024-02-04 · Long Ma, Yuanfei Wang, Fangwei Zhong, Song-Chun Zhu 외

Fast adapting to unknown peers (partners or opponents) with different strategies is a key challenge in multi-agent games. To do so, it is crucial for the agent to probe and identify the peer's strategy efficiently, as th…

Wonder Wins Ways: Curiosity-Driven Exploration through Multi-Agent Contextual Calibration

2025-09-25 · Yiyuan Pan, Zhe Liu, Hesheng Wang arxiv

Autonomous exploration in complex multi-agent reinforcement learning (MARL) with sparse rewards critically depends on providing agents with effective intrinsic motivation. While artificial curiosity offers a powerful sel…

Multi-agent Reinforcement Learning

DRAFT-RL: Multi-Agent Chain-of-Draft Reasoning for Reinforcement Learning-Enhanced LLMs

2025-11-25 · Yuanhao Li, Mingshan Liu, Hongbo Wang, Yiding Zhang 외 arxiv

Large Language Models (LLMs) have shown impressive capabilities in multi-step reasoning and problem-solving.Recent works introduce multi-agent reflection frameworks where multiple LLM agents critique and refine each othe…

Reinforcement Learning

AgentReview: Exploring Peer Review Dynamics with LLM Agents

2024-06-18 · Yiqiao Jin, Qinlin Zhao, Yiyang Wang, Hao Chen 외

Peer review is fundamental to the integrity and advancement of scientific publication. Traditional methods of peer review analyses often rely on exploration and statistics of existing peer review data, which do not adequ…

Language ModelingLanguage ModellingLarge Language Model