{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T20:09:35Z","timestamp":1730232575338,"version":"3.28.0"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,28]],"date-time":"2023-05-28T00:00:00Z","timestamp":1685232000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,28]],"date-time":"2023-05-28T00:00:00Z","timestamp":1685232000000},"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":[[2023,5,28]]},"DOI":"10.1109\/icc45041.2023.10279625","type":"proceedings-article","created":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T17:54:10Z","timestamp":1698083650000},"page":"466-471","source":"Crossref","is-referenced-by-count":2,"title":["On Learning Intrinsic Rewards for Faster Multi-Agent Reinforcement Learning based MAC Protocol Design in 6G Wireless Networks"],"prefix":"10.1109","author":[{"given":"Luciano","family":"Miuccio","sequence":"first","affiliation":[{"name":"University of Catania,Department of Electrical, Electronics and Computer Engineering,Italy"}]},{"given":"Salvatore","family":"Riolo","sequence":"additional","affiliation":[{"name":"University of Catania,Department of Electrical, Electronics and Computer Engineering,Italy"}]},{"given":"Mehdi","family":"Bennis","sequence":"additional","affiliation":[{"name":"University of Oulu,Centre for Wireless Communications,Finland"}]},{"given":"Daniela","family":"Panno","sequence":"additional","affiliation":[{"name":"University of Catania,Department of Electrical, Electronics and Computer Engineering,Italy"}]}],"member":"263","reference":[{"volume-title":"Emergent multi-agent communication in the deep learning era","year":"2020","author":"Lazaridou","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2021.3080677"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM48099.2022.10000805"},{"volume-title":"Dealing with non-stationarity in multi-agent deep reinforcement learning","year":"2019","author":"Papoudakis","key":"ref4"},{"volume-title":"Parameter sharing deep deterministic policy gradient for cooperative multi-agent reinforcement learning","year":"2017","author":"Chu","key":"ref5"},{"key":"ref6","first-page":"4644","article-title":"On learning intrinsic rewards for policy gradient methods","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems, ser. NIPS18","author":"Zheng"},{"volume-title":"What can learned intrinsic rewards capture?","year":"2019","author":"Zheng","key":"ref7"},{"volume-title":"Reinforcement learning: An introduction","year":"2018","author":"Sutton","key":"ref8"},{"key":"ref9","article-title":"The surprising effectiveness of MAPPO in cooperative, multi-agent games","volume":"abs\/2103.01955","author":"Yu","year":"2021","journal-title":"CoRR"},{"key":"ref10","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume-title":"CoRR","volume":"abs\/1412.3555","author":"Chung","year":"2014"},{"key":"ref11","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Advances in Neural Information Processing Systems","volume":"12","author":"Sutton","year":"1999"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"volume-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref13"},{"key":"ref14","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","author":"Schulman"},{"volume-title":"Continual meta-reinforcement learning for UAV-aided vehicular wireless networks","year":"2022","author":"Marini","key":"ref15"}],"event":{"name":"ICC 2023 - IEEE International Conference on Communications","start":{"date-parts":[[2023,5,28]]},"location":"Rome, Italy","end":{"date-parts":[[2023,6,1]]}},"container-title":["ICC 2023 - IEEE International Conference on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10278505\/10278554\/10279625.pdf?arnumber=10279625","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T09:02:13Z","timestamp":1709370133000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10279625\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,28]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/icc45041.2023.10279625","relation":{},"subject":[],"published":{"date-parts":[[2023,5,28]]}}}