2 papers
cs.AI2026
Regularized Emphatic Temporal-Difference Learning: Stability under Constant Stepsizes
Xingguo Chen, Zhaohui Wu, Jinguo Ye +5
Emphatic temporal-difference learning (ETD) stabilizes the expected off-policy TD update and changes its projection geometry, but neither property determines constant-stepsize samp…
cs.AI2026
Regularized Centered Emphatic Temporal Difference Learning
Xingguo Chen, Chaohui Wu, Jinguo Ye +5
Off-policy temporal-difference (TD) learning with function approximation faces a structural tradeoff among stability, projection geometry, and variance control. Emphatic TD (ETD) i…