{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:31:13Z","timestamp":1776882673366,"version":"3.51.2"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890857","type":"proceedings-article","created":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T13:33:09Z","timestamp":1741699989000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Role-Specific Reward Design with Large Language Model for StarCraft II"],"prefix":"10.1109","author":[{"given":"Sijia","family":"Li","sequence":"first","affiliation":[{"name":"School of Computing and Artificial Intelligence,Southwest Jiaotong University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haonan","family":"Lou","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence,Southwest Jiaotong University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, School of Computer Science and Engineering, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence,Southwest Jiaotong University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhixuan","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence,Southwest Jiaotong University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianrui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence,Southwest Jiaotong University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A survey on large language model-based game agents","author":"Hu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Ghost in the minecraft: Generally capable agents for open-world environments via large language models with text-based knowledge and memory","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Large language models as generalizable policies for embodied tasks","volume-title":"The Twelfth International Conference on Learning Representations","author":"Szot","year":"2023"},{"key":"ref4","article-title":"Large language models play starcraft ii: Benchmarks and a chain of summarization approach","author":"Ma","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3109284"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref9","article-title":"The starcraft multi-agent challenge","author":"Samvelyan","year":"2019","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Reinforcement Learning: An Introduction","volume-title":"MIT Press","author":"Sutton","year":"2018"},{"key":"ref11","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proceedings of the Sixteenth International Conference on Machine Learning (ICML)","author":"Ng","year":"1999"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i5.25733"},{"key":"ref13","volume-title":"Temporal credit assignment in reinforcement learning","author":"Sutton","year":"1984"},{"key":"ref14","article-title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","volume":"abs\/1803.11485","author":"Rashid","year":"2018","journal-title":"ArXiv"},{"key":"ref15","article-title":"Disentangling Sources of Risk for Distributional MultiAgent Reinforcement Learning","volume-title":"International Conference on Machine Learning","author":"Son","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3497992"},{"key":"ref17","article-title":"Reward design with language models","author":"Kwon","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","author":"Carta","year":"2023","journal-title":"Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning"},{"key":"ref19","author":"Ma","year":"2023","journal-title":"Eureka: HumanLevel Reward Design via Coding Large Language Models"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.153"},{"key":"ref21","article-title":"Value-decomposition networks for cooperative multi-agent learning","volume-title":"AAMAS\u201918: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems","author":"Sunehag","year":"2018"},{"key":"ref22","article-title":"Dfac framework: Factorizing the value function via quantile mixture for multi-agent distributional q-learning","volume-title":"International Conference on Machine Learning","author":"Sun","year":"2021"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890857.pdf?arnumber=10890857","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:41Z","timestamp":1774416161000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890857\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890857","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}