{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:46:46Z","timestamp":1781714806601,"version":"3.54.5"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,8]]},"abstract":"<jats:p>Deep Reinforcement Learning (DRL) has been applied\u00a0to address a variety of cooperative multi-agent problems with either discrete action spaces or continuous action spaces. However, to the best of our knowledge, no previous work has ever succeeded\u00a0in applying DRL to multi-agent problems with discrete-continuous hybrid (or parameterized) action spaces which is very common in practice. Our work fills this gap by proposing two novel algorithms: Deep Multi-Agent Parameterized Q-Networks (Deep MAPQN) and Deep Multi-Agent Hierarchical Hybrid Q-Networks (Deep MAHHQN). We follow the centralized training but decentralized execution paradigm: different levels of communication between different agents are used to facilitate the training process, while each agent executes its policy independently based on local observations during execution. Our empirical results on several challenging tasks (simulated RoboCup Soccer and game Ghost Story) show that both Deep MAPQN and Deep MAHHQN are effective and significantly outperform existing independent deep parameterized Q-learning method.<\/jats:p>","DOI":"10.24963\/ijcai.2019\/323","type":"proceedings-article","created":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T03:46:05Z","timestamp":1564285565000},"page":"2329-2335","source":"Crossref","is-referenced-by-count":47,"title":["Deep Multi-Agent Reinforcement Learning with Discrete-Continuous Hybrid Action Spaces"],"prefix":"10.24963","author":[{"given":"Haotian","family":"Fu","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyao","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianye","family":"Hao","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihan","family":"Lei","sequence":"additional","affiliation":[{"name":"Fuxi AI Lab in Netease"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingfeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Fuxi AI Lab in Netease"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changjie","family":"Fan","sequence":"additional","affiliation":[{"name":"Fuxi AI Lab in Netease"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10584","event":{"name":"Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}","theme":"Artificial Intelligence","location":"Macao, China","acronym":"IJCAI-2019","number":"28","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2019,8,10]]},"end":{"date-parts":[[2019,8,16]]}},"container-title":["Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T03:48:33Z","timestamp":1564285713000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2019\/323"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2019\/323","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}