paper-with-me

홈 › Papers

MIR: Efficient Exploration in Episodic Multi-Agent Reinforcement Learning via Mutual Intrinsic Reward

2025-11-21 · Kesheng Chen, Wenjian Luo, Bang Zhang, Zeping Yin, Zipeng Ye arxiv

Episodic rewards present a significant challenge in reinforcement learning. While intrinsic reward methods have demonstrated effectiveness in single-agent rein-forcement learning scenarios, their application to multi-agent reinforcement learn-ing (MARL) remains problematic. The primary difficulties stem from two fac-tors: (1) the exponential sparsity of joint action trajectories that lead to rewards as the exploration space expands, and (2) existing methods often fail to account for joint actions that can influence team states. To address these challenges, this paper introduces Mutual Intrinsic Reward (MIR), a simple yet effective enhancement strategy for MARL with extremely sparse rewards like episodic rewards. MIR incentivizes individual agents to explore actions that affect their teammates, and when combined with original strategies, effectively stimulates team exploration and improves algorithm performance. For comprehensive experimental valida-tion, we extend the representative single-agent MiniGrid environment to create MiniGrid-MA, a series of MARL environments with sparse rewards. Our evalu-ation compares the proposed method against state-of-the-art approaches in the MiniGrid-MA setting, with experimental results demonstrating superior perfor-mance.

📄 PDF Abstract BibTeX arXiv:2511.17165

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning

Similar Papers 제목 키워드 기반

Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Exploration

2021-11-22 · NeurIPS 2021 12 · Lulu Zheng, Jiarui Chen, Jianhao Wang, Jiamin He 외

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 learn…

Efficient ExplorationMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning+3

Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory

2025-12-08 · Sijia Li, Yuchen Huang, Zifan Liu, Zijian Li 외 arxiv

As intents unfold and environments change, multi-turn agents face continuously shifting decision contexts. Although reusing past experience is intuitively appealing, existing approaches remain limited: full trajectories …

Reinforcement Learning

DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewards

2023-04-21 · Shanchuan Wan, Yujin Tang, Yingtao Tian, Tomoyuki Kaneko

Exploration is a fundamental aspect of reinforcement learning (RL), and its effectiveness is a deciding factor in the performance of RL algorithms, especially when facing sparse extrinsic rewards. Recent studies have sho…

Reinforcement Learning (RL)

Remember to be Curious: Episodic Context and Persistent Worlds for 3D Exploration

2026-05-21 · Lily Goli, Justin Kerr, Daniele Reda, Alec Jacobson 외 arxiv

Exploration is a prerequisite for learning useful behaviors in sparse-reward, long-horizon tasks, particularly within 3D environments. Curiosity-driven reinforcement learning addresses this via intrinsic rewards derived …

Reinforcement Learning3D Reconstruction

Extending NGU to Multi-Agent RL: A Preliminary Study

2025-12-01 · Juan Hernandez, Diego Fernández, Manuel Cifuentes, Denis Parra 외 arxiv

The Never Give Up (NGU) algorithm has proven effective in reinforcement learning tasks with sparse rewards by combining episodic novelty and intrinsic motivation. In this work, we extend NGU to multi-agent environments a…

Reinforcement Learning