method · first seen 4 Oct 2026
successor measure
Also: successor features
A representation of expected discounted future state occupancy that enables fast policy evaluation across reward functions.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Task Inference Beyond Least Squares in Behavioral Foundation ModelsPapers · 4 Oct 2026 · Kuan-Hsun Tu, Chien-Sheng Chiang, Hsin-Wei Chen, Ping-Chun Hsieh, Tsung-Wei Ke
- Uncertainty-Guided Reward Labeling for Reinforcement Learning under Limited FeedbackPapers · 8 Nov 2026 · Renhao Zhang, Shreyas Chaudhari, Bruno Castro da Silva
Latest sources
- Uncertainty-Guided Reward Labeling for Reinforcement Learning under Limited FeedbackPapers · 8 Nov 2026 · Renhao Zhang, Shreyas Chaudhari, Bruno Castro da Silva
- Task Inference Beyond Least Squares in Behavioral Foundation ModelsPapers · 4 Oct 2026 · Kuan-Hsun Tu, Chien-Sheng Chiang, Hsin-Wei Chen, Ping-Chun Hsieh, Tsung-Wei Ke