{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T00:32:33Z","timestamp":1725496353675},"reference-count":13,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T00:00:00Z","timestamp":1716163200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T00:00:00Z","timestamp":1716163200000},"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":[[2024,5,20]]},"DOI":"10.1109\/icdl61372.2024.10644943","type":"proceedings-article","created":{"date-parts":[[2024,8,27]],"date-time":"2024-08-27T17:19:46Z","timestamp":1724779186000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Improving Proximal Policy Optimization Algorithm in Interactive Multi-Agent Systems"],"prefix":"10.1109","author":[{"given":"Yi","family":"Shang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of New South Wales,Sydney,NSW,Australia"}]},{"given":"Yifei","family":"Chen","sequence":"additional","affiliation":[{"name":"Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen,The Netherlands"}]},{"given":"Francisco","family":"Cruz","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of New South Wales,Sydney,NSW,Australia"}]}],"member":"263","reference":[{"volume-title":"Reinforcement Learning: An Introduction","year":"2020","author":"Sutton","key":"ref1"},{"key":"ref2","first-page":"661","article-title":"Human feedback in continuous actor-critic reinforcement learning","volume-title":"Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)","author":"Mill\u00e1n","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2017.8329809"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2997896"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s43684-022-00023-5"},{"key":"ref7","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"journal-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","year":"2018","author":"Haarnoja","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"journal-title":"Addressing function approximation error in actor-critic methods","year":"2018","author":"Fujimoto","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"journal-title":"Parameter sharing deep deterministic policy gradient for cooperative multi-agent reinforcement learning","year":"2017","author":"Chu","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26379"}],"event":{"name":"2024 IEEE International Conference on Development and Learning (ICDL)","start":{"date-parts":[[2024,5,20]]},"location":"Austin, TX, USA","end":{"date-parts":[[2024,5,23]]}},"container-title":["2024 IEEE International Conference on Development and Learning (ICDL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10644131\/10644157\/10644943.pdf?arnumber=10644943","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T06:36:08Z","timestamp":1725431768000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10644943\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,20]]},"references-count":13,"URL":"https:\/\/doi.org\/10.1109\/icdl61372.2024.10644943","relation":{},"subject":[],"published":{"date-parts":[[2024,5,20]]}}}