Abstract:Many Multi-Agent Reinforcement Learning (MARL) agents fail to adapt properly to cooperating with agents trained with the same objectives but different seeds, algorithms, or other training differences. This is the problem of Zero-Shot Coordination (ZSC), which focuses on training agents to cooperate well with unknown agents. ZSC has been studied for a variety of tabular cases and simple games such as Hanabi, achieving excellent results. However, existing solutions to ZSC only consider identical rewards for your trained agents and all future partners. This is not realistic for the trained agents, as they do not consider the problem of cooperating with agents that have identical sparse objectives but shape the rewards for those objectives in different manner. To address this issue, we show how to train an ensemble of methods using randomized reward shapings chosen using 4 selection algorithms. Experiments done on the Overcooked environment demonstrate consistent improvements of 62.2%-119.2% in sparse reward over baseline ZSC algorithms when playing with agents that have identical sparse rewards but different reward shapings.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2604.25076 [cs.LG] |
| (or arXiv:2604.25076v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.25076 arXiv-issued DOI via DataCite (pending registration) |
From: Keenan Powell [view email]
[v1]
Tue, 28 Apr 2026 00:09:28 UTC (393 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。