{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,17]],"date-time":"2026-11-17T12:18:26Z","timestamp":1794917906621,"version":"4.9.1"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:p>Zero-shot transfer for offline reinforcement learning involves generalizing to a wide range of tasks that are often risk-sensitive, without new interaction. We show here that although Successor Features (SFs) provide a principled framework for transfer through abstracting dynamics from rewards, their typical form is restricted to expected cumulative returns and is thus indifferent to variance in returns. We contend that such a mean-centric approach introduces bias by conflating risky and safe trajectories with identical expected outcomes, as it ignores outcome dispersion critical for risk-aware evaluation. Additionally, we note that distributional methods can be employed to model outcome distributions, but frequently do so at a high computational cost due to the need for discretization or elaborate sampling. To overcome this problem, we introduce a form of successor representation that incorporates an uncertainty envelope over states: Gaussian Distributional Successor Features (GDSF). Rather than inferring an implicit generative process, GDSF learns to approximate the distribution of cumulative outcomes with a Gaussian through recursive moment-matching. We present this framework for efficient representation of aleatoric uncertainty, without resorting to computationally expensive existing distributional methods. We also introduce Latent Outcome  Optimization, an inference procedure which finds high-reward outcomes in the data support and drives a goal-conditioned policy. This dual-mode design allows the agent to transfer to non-linear objectives in a zero-shot way while preserving closed-form efficiency for linear tasks. Experiments on the D4RL benchmark show that GDSF yields better performance in risk-sensitive tasks while achieving at least competitive results in standard linear regimes.<\/jats:p>","DOI":"10.24963\/ijcai.2026\/601","type":"proceedings-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T22:01:13Z","timestamp":1789596073000},"page":"5396-5403","source":"Crossref","is-referenced-by-count":0,"title":["Beyond the Mean: Gaussian Distributional Successor Features for Zero-Shot Non-Linear Reward Adaptation"],"prefix":"10.24963","author":[{"given":"Yong","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Cybersecurity, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Cybersecurity, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhua","family":"He","sequence":"additional","affiliation":[{"name":"School of Computer Science and Electronic Engineering, University of Essex, Colchester, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"Generative AI Research & Development Center, HKGAI, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qubeijian","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Cybersecurity, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10584","event":{"name":"Thirty-Fifth International Joint Conference on Artificial Intelligence {IJCAI-26}","theme":"Artificial Intelligence","location":"Bremen, Germany","acronym":"IJCAI-2026","number":"35","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2026,8,15]]},"end":{"date-parts":[[2026,8,21]]}},"container-title":["Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2026,11,17]],"date-time":"2026-11-17T11:30:51Z","timestamp":1794915051000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2026\/601"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2026\/601","relation":{},"subject":[],"published":{"date-parts":[[2026,9]]}}}