{"type":"ScholarlyArticle","title":"Beyond the Mean: Gaussian Distributional Successor Features for Zero-Shot Non-Linear Reward Adaptation","authors":[{"name":"Yong Zhao","slug":"yong-zhao","given":"Yong","family":"Zhao","affiliation":""},{"name":"Wen Sun","slug":"wen-sun","given":"Wen","family":"Sun","affiliation":""},{"name":"Jianhua He","slug":"jianhua-he","given":"Jianhua","family":"He","affiliation":""},{"name":"Peng Wang","slug":"peng-wang","given":"Peng","family":"Wang","affiliation":""},{"name":"Qubeijian Wang","slug":"qubeijian-wang","given":"Qubeijian","family":"Wang","affiliation":""}],"abstract":"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.","doi":"10.24963/ijcai.2026/601","url":"https://ijcai.org/proceedings/2026/601","pdf":"https://ijcai.org/proceedings/2026/0601.pdf","markdown":"https://ijcai.org/proceedings/2026/601.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/601","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Machine Learning","track":"Main Track","number":601,"pages":{"first":5396,"last":5403},"keywords":["Machine Learning: Offline reinforcement learning","Machine Learning: Multi-task and transfer learning","Planning and Scheduling: Planning under uncertainty","Machine Learning: Model-based and model learning reinforcement learning","Machine Learning: Reinforcement learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}