Showing stat.MLShow all
2 papers · 1 filter
stat.ML2026
Neural Actor--Critic Learning with Minimax Critics and Reflected Langevin Sampling
Kunqi Huang, Lican Kang, Hongrui Shu +1
Actor--critic methods rely on critic gradients to improve continuous-action policies, yet finite-sample guarantees must control both value and gradient errors and their propagation…
stat.ML2026
Schrödinger--Föllmer Actor--Critic: Diffusion Policy Improvement with Finite-Sample Analysis
Yuling Jiao, Lican Kang, Jerry Zhijian Yang +1
Diffusion policies represent multimodal action distributions, but a -weighted update does not specify how to sample from the resulting target distribution. We propose Schrödinge…