{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:46:00Z","timestamp":1782798360489,"version":"3.54.5"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"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":[[2026,5,18]]},"DOI":"10.1109\/infocom59046.2026.11571525","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:38:15Z","timestamp":1782761895000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Remote Reinforcement Learning over Unreliable Channels with Homomorphic State Representations"],"prefix":"10.1109","author":[{"given":"Pietro","family":"Talli","sequence":"first","affiliation":[{"name":"University of Padova,Department of Information Engineering,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Federico","family":"Mason","sequence":"additional","affiliation":[{"name":"University of Padova,Department of Information Engineering,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Federico","family":"Chiariotti","sequence":"additional","affiliation":[{"name":"University of Padova,Department of Information Engineering,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Zanella","sequence":"additional","affiliation":[{"name":"University of Padova,Department of Information Engineering,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME58846.2023.00015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3087248"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/2200000086"},{"key":"ref4","first-page":"12 519","article-title":"When to trust your model: Model-based policy optimization","volume-title":"Proc. 33rd Conf. Neur. Inf. Proc. Sys. (NeurIPS)","author":"Janner"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2024.3416202"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1287\/opre.21.5.1071"},{"key":"ref8","first-page":"2123","article-title":"Reinforcement learning from delayed observations via world models","volume":"5","author":"Karamzade","year":"2025","journal-title":"Reinf. Learning J."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2025.3559152"},{"key":"ref10","first-page":"15 650","article-title":"Reinforcement learning with state observation costs in action-contingent noiselessly observable markov decision processes","volume-title":"Proc. 35th Conf. Neur. Inf. Proc. Sys. (NeurIPS)","author":"Nam"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2919300"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3349330"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3126087"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-08744-2"},{"key":"ref15","first-page":"4199","article-title":"MDP homomorphic networks: Group symmetries in reinforcement learning","volume-title":"Proc. 34th Conf. Neur. Inf. Proc. Sys. (NeurIPS)","author":"Van der Pol"},{"key":"ref16","first-page":"1011","article-title":"SMDP homomorphisms: an algebraic approach to abstraction in semi-Markov decision processes","volume-title":"Proc. 18th Int. Joint Conf. Artif. Intell. (IJCAI)","author":"Ravindran"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1993.5.4.613"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1582"},{"key":"ref19","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015"},{"key":"ref20","first-page":"2566","article-title":"How learning by reconstruction produces uninformative features for perception","volume-title":"Proc. 41st Int. Conf. Machine Learning (ICML)","author":"Balestriero"},{"key":"ref21","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25864"},{"issue":"268","key":"ref23","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"J. Machine Learning Res."},{"key":"ref24","article-title":"Deepmind control suite","author":"Tassa","year":"2018"}],"event":{"name":"IEEE INFOCOM 2026 - IEEE Conference on Computer Communications","location":"Tokyo, Japan","start":{"date-parts":[[2026,5,18]]},"end":{"date-parts":[[2026,5,21]]}},"container-title":["IEEE INFOCOM 2026 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11571071\/11571169\/11571525.pdf?arnumber=11571525","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:29:33Z","timestamp":1782797373000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11571525\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/infocom59046.2026.11571525","relation":{},"subject":[],"published":{"date-parts":[[2026,5,18]]}}}