Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Q-Learning with Scalar Adjoint Matching
Yonghoon Dong, Minsung Yoon, Jaehyuk Kim +3
Flow policies capture rich and diverse action distributions, and fine-tuning them with off-policy RL to improve beyond the demonstrations has drawn growing interest. However, fine-…
cs.LG2026
Trust Region Q Adjoint Matching
Yonghoon Dong, Kyungmin Lee, Changyeon Kim +2
Off-policy reinforcement learning of pretrained flow policies remains challenging due to the instability of optimization arising from the multi-step sampling process. Recently, Q-l…