Stochastic Control; Reinforcement Learning; Diffusion Policy; Continuous Q-Learning; Martingale Orthogonality Condition - NeurIPS 2025

today local_bar

Stochastic Control; Reinforcement Learning; Diffusion Policy; Continuous Q-Learning; Martingale Orthogonality Condition

1 paper across 1 session

Poster Session 3

Thursday, December 4, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Continuous Q-Score Matching: Diffusion Guided Reinforcement Learning for Continuous-Time Control

#3100 · Chengxiu HUA, Jiawen Gu, Yushun Tang

We introduced a Q-function framework for continuous-time reinforcement learning and develope the Continuous Q-Score Matching (CQSM) algorithm.