AI RESEARCH

Q-learning with Adjoint Matching

arXiv CS.AI

ArXi:2601.14234v3 Announce Type: replace-cross We propose Q-learning with Adjoint Matching (QAM), a novel TD-based reinforcement learning (RL) algorithm that tackles a long-standing challenge in continuous-action RL: efficient optimization of an expressive diffusion or flow-matching policy with respect to a parameterized Q-function.