{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:04:59Z","timestamp":1773803099150,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"27","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Deep reinforcement learning has proven to be a powerful approach to solving control tasks, but its characteristic high\u2011frequency oscillations make it difficult to apply in real\u2011world environments.\nWhile prior methods have addressed action oscillations via architectural or loss-based methods, the latter typically depend on heuristic or synthetic definitions of state similarity to promote action consistency, which often fail to accurately reflect the underlying system dynamics.\nIn this paper, we propose a novel loss-based method by introducing a transition-induced similar state.\nThe transition-induced similar state is defined as the distribution of next states transitioned from the previous state.\nSince it utilizes only environmental feedback and actually collected data, it better captures system dynamics.\nBuilding upon this foundation, we introduce Action Smoothing by Aligning Actions with Predictions from Preceding States (ASAP), an action smoothing method that effectively mitigates action oscillations. \nASAP enforces action smoothness by aligning the actions with those taken in transition-induced similar states and by penalizing second-order differences to suppress high-frequency oscillations.\nExperiments in Gymnasium and Isaac-lab environments demonstrate that ASAP yields smoother control and improved policy performance over existing methods.<\/jats:p>","DOI":"10.1609\/aaai.v40i27.39432","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:33:37Z","timestamp":1773797617000},"page":"22707-22715","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Control Policy Smoothness by Aligning Actions with Predictions from Preceding States"],"prefix":"10.1609","volume":"40","author":[{"given":"Kyoleen","family":"Kwak","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyoseok","family":"Hwang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/39432\/43393","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/39432\/43393","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:33:37Z","timestamp":1773797617000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/39432"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"27","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i27.39432","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}