thu-ml/SRPO

Codes accompanying the paper "Score Regularized Policy Optimization through Diffusion Behavior" (ICLR 2024).

语言：Python · GitHub 星标：48 · Fork：3

话题：behavior-regularization · d4rl · diffusion · generative · offline · reinforcement-learning · rl · score-based-models

在 GitHub 上查看原仓库