{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:13:17Z","timestamp":1763190797016,"version":"3.45.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227565","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["A Reinforcement Learning Method for Environments with Stochastic Variables: Post-Decision Proximal Policy Optimization with Dual Critic Networks"],"prefix":"10.1109","author":[{"given":"Leonardo Kanashiro","family":"Felizardo","sequence":"first","affiliation":[{"name":"Instituto Tecnológico de Aeronáutica,Division of Computer Science,São Paulo,Brazil"}]},{"given":"Edoardo","family":"Fadda","sequence":"additional","affiliation":[{"name":"Politecnico di Torino,Department of Mathematical Sciences,Turin,Italy"}]},{"given":"Paolo","family":"Brandimarte","sequence":"additional","affiliation":[{"name":"Politecnico di Torino,Department of Mathematical Sciences,Turin,Italy"}]},{"given":"Emilio","family":"Del-Moral-Hernandez","sequence":"additional","affiliation":[{"name":"Universidade de São Paulo,Escola Politécnica,São Paulo,Brazil"}]},{"given":"Mari\u00e1 Cristina Vasconcelos","family":"Nascimento","sequence":"additional","affiliation":[{"name":"Instituto Tecnológico de Aeronáutica,Division of Computer Science,São José dos Campos,Brazil"}]}],"member":"263","reference":[{"key":"ref1","first-page":"35921","article-title":"Dna: Proximal policy optimization with a dual network architecture","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Aitchison","year":"2022"},{"volume-title":"DynamicProgramming. Rand Corporation research study","year":"1957","author":"Bellman","key":"ref2"},{"journal-title":"Dynamic Programming and Optimal Control, Vol. II","year":"2007","author":"Bertsekas","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-61867-4"},{"journal-title":"Phasic policy gradient","year":"2020","author":"Cobbe","key":"ref5"},{"article-title":"Implementation matters in deep rl: A case study on ppo and trpo","volume-title":"International Conference on Learning Representations","author":"Engstrom","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.123036"},{"journal-title":"Addressing function approximation error in actor-critic methods","year":"2018","author":"Fujimoto","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3117855"},{"journal-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","year":"2018","author":"Haarnoja","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.11.025"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jedc.2015.03.008"},{"journal-title":"Doubly robust off-policy actor-critic algorithms for reinforcement learning","year":"2019","author":"Islam","key":"ref14"},{"key":"ref15","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Advances in Neural Information Processing Systems 32","author":"Paszke","year":"2019"},{"journal-title":"Empirical design in reinforcement learning","year":"2023","author":"Patterson","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17130"},{"journal-title":"Decoupling value and policy for generalization in reinforcement learning","year":"2021","author":"Raileanu","key":"ref19"},{"key":"ref20","volume-title":"On-line Q-learning using connectionist systems","volume":"37","author":"Rummery","year":"1994"},{"key":"ref21","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proceedings of the 32nd International Conference on Machine Learning, volume 37 of Proceedings of Machine Learning Research","author":"Schulman"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.06347"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2014.01.002"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2022.2056540"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CAC57257.2022.10055040"},{"key":"ref26","article-title":"Learning from Delayed Rewards","volume-title":"PhD thesis","author":"John Cornish Hellaby Watkins","year":"1989"},{"journal-title":"The surprising effectiveness of ppo in cooperative, multi-agent games","year":"2022","author":"Yu","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3242613"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.07.111"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.07.111"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227565.pdf?arnumber=11227565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:10:13Z","timestamp":1763190613000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227565\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227565","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}