中文
相关论文

相关论文: MIR: Efficient Exploration in Episodic Multi-Agent…

200 篇论文

Efficient exploration in multi-agent reinforcement learning (MARL) is a challenging problem when receiving only a team reward, especially in environments with sparse rewards. A powerful method to mitigate this issue involves crafting dense…

机器学习 · 计算机科学 2025-07-28 Xuefei Wu , Xiao Yin , Yuanyang Zhu , Chunlin Chen

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…

机器学习 · 计算机科学 2021-11-23 Lulu Zheng , Jiarui Chen , Jianhao Wang , Jiamin He , Yujing Hu , Yingfeng Chen , Changjie Fan , Yang Gao , Chongjie Zhang

In cooperative multi-agent reinforcement learning (MARL), agents aim to achieve a common goal, such as defeating enemies or scoring a goal. Existing MARL algorithms are effective but still require significant learning time and often get…

机器学习 · 计算机科学 2024-03-08 Hyungho Na , Yunkyeong Seo , Il-chul Moon

Solving tasks with sparse rewards is one of the most important challenges in reinforcement learning. In the single-agent setting, this challenge is addressed by introducing intrinsic rewards that motivate agents to explore unseen regions of…

机器学习 · 计算机科学 2021-05-25 Shariq Iqbal , Fei Sha

Multi-agent deep reinforcement learning (MADRL) problems often encounter the challenge of sparse rewards. This challenge becomes even more pronounced when coordination among agents is necessary. As performance depends not only on one…

多智能体系统 · 计算机科学 2024-02-07 Maxime Toquebiau , Nicolas Bredeche , Faïz Benamar , Jae-Yun Jun

Deducing the contribution of each agent and assigning the corresponding reward to them is a crucial problem in cooperative Multi-Agent Reinforcement Learning (MARL). Previous studies try to resolve the issue through designing an intrinsic…

机器学习 · 计算机科学 2023-02-21 Wei Li , Weiyan Liu , Shitong Shao , Shiyi Huang

Exploration in sparse reward environments remains one of the key challenges of model-free reinforcement learning. Instead of solely relying on extrinsic rewards provided by the environment, many state-of-the-art methods use intrinsic…

机器学习 · 计算机科学 2020-03-03 Roberta Raileanu , Tim Rocktäschel

Discovering successful coordinated behaviors is a central challenge in Multi-Agent Reinforcement Learning (MARL) since it requires exploring a joint action space that grows exponentially with the number of agents. In this paper, we propose…

机器学习 · 计算机科学 2021-10-14 Ammar Fayad , Majd Ibrahim

Intrinsic rewards have been increasingly used to mitigate the sparse reward problem in single-agent reinforcement learning. These intrinsic rewards encourage the agent to look for novel experiences, guiding the agent to explore the…

人工智能 · 计算机科学 2022-11-01 Roben Delos Reyes , Kyunghwan Son , Jinhwan Jung , Wan Ju Kang , Yung Yi

Efficient exploration is important for reinforcement learners to achieve high rewards. In multi-agent systems, coordinated exploration and behaviour is critical for agents to jointly achieve optimal outcomes. In this paper, we introduce a…

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 shown the effectiveness…

机器学习 · 计算机科学 2023-05-19 Shanchuan Wan , Yujin Tang , Yingtao Tian , Tomoyuki Kaneko

In this paper, we study cooperative multi-agent reinforcement learning (MARL) where the joint reward exhibits submodularity, which is a natural property capturing diminishing marginal returns when adding agents to a team. Unlike standard…

机器学习 · 计算机科学 2026-03-10 Wenjing Chen , Chengyuan Qian , Shuo Xing , Yi Zhou , Victoria Crawford

Games are challenging for Reinforcement Learning~(RL) agents due to their reward-sparsity, as rewards are only obtainable after long sequences of deliberate actions. Intrinsic Motivation~(IM) methods -- which introduce exploration rewards…

人工智能 · 计算机科学 2025-07-29 Leonardo Villalobos-Arias , Grant Forbes , Jianxun Wang , David L Roberts , Arnav Jhala

Training a multi-agent reinforcement learning (MARL) model with a sparse reward is generally difficult because numerous combinations of interactions among agents induce a certain outcome (i.e., success or failure). Earlier studies have…

机器学习 · 计算机科学 2022-02-08 Heechang Ryu , Hayong Shin , Jinkyoo Park

In this paper, we consider cooperative multi-agent reinforcement learning (MARL) with sparse reward. To tackle this problem, we propose a novel method named MASER: MARL with subgoals generated from experience replay buffer. Under the…

机器学习 · 计算机科学 2022-06-23 Jeewon Jeon , Woojun Kim , Whiyoung Jung , Youngchul Sung

Cooperative multi-agent reinforcement learning (MARL) requires agents to discover joint strategies in a combinatorially large state-action space, yet effective coordination configurations are exceedingly rare. Intrinsic motivation, which…

多智能体系统 · 计算机科学 2026-05-05 Dahyun Oh , Minhyuk Yoon , H. Jin Kim

A key challenge in multi-agent reinforcement learning (MARL) lies in designing learning signals that effectively promote coordination among agents. Designing such signals requires estimating how one agent's current action affects its…

多智能体系统 · 计算机科学 2026-05-12 Haohan Yu , Jinmiao Cong , Shengzhi Wang , Lu Wang , Chanjuan Liu

Multi-agent reinforcement learning (MARL) has achieved great progress in cooperative tasks in recent years. However, in the local reward scheme, where only local rewards for each agent are given without global rewards shared by all the…

机器学习 · 计算机科学 2023-02-21 Yunbo Qiu , Yue Jin , Lebin Yu , Jian Wang , Xudong Zhang

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 problem is the less…

机器学习 · 计算机科学 2019-12-30 Qisheng Wang , Qichao Wang

Many scenes in real life can be abstracted to the sparse reward visual scenes, where it is difficult for an agent to tackle the task under the condition of only accepting images and sparse rewards. We propose to decompose this problem into…

人工智能 · 计算机科学 2022-05-20 Zheng Fang , Biao Zhao , Guizhong Liu
‹ 上一页 1 2 3 10 下一页 ›