{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:18:20Z","timestamp":1773803900637,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"32","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>In many practical reinforcement learning tasks, feedback is only provided at the end of a long horizon, leading to sparse and delayed rewards. Existing reward redistribution methods typically assume that per-step rewards are independent, thus overlooking interdependencies among state\u2013action pairs. In this paper, we propose a Gaussian Process-based Likelihood Reward Redistribution (GP-LRR) framework that addresses this issue by modeling the reward function as a sample from a Gaussian Process (GP), which explicitly captures dependencies between state\u2013action pairs through the kernel function. By maximizing the likelihood of the observed episodic return via a leave-one-out strategy that leverages the entire trajectory, our framework inherently introduces uncertainty regularization. Moreover, we show that the conventional mean squared error (MSE)-based reward redistribution arises as a special case of our GP-LRR framework when using a degenerate kernel without observation noise. When integrated with an off-policy algorithm such as Soft Actor-Critic, GP-LRR yields dense and informative reward signals, resulting in superior sample efficiency and policy performance on several MuJoCo benchmarks.<\/jats:p>","DOI":"10.1609\/aaai.v40i32.39921","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:12:15Z","timestamp":1773799935000},"page":"27073-27080","source":"Crossref","is-referenced-by-count":0,"title":["Reward Redistribution via Gaussian Process Likelihood Estimation"],"prefix":"10.1609","volume":"40","author":[{"given":"Minheng","family":"Xiao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xian","family":"Yu","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\/39921\/43882","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/39921\/43882","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:12:15Z","timestamp":1773799935000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/39921"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"32","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i32.39921","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]]}}}