thu-ml / SRPO Star 48 Code Issues Pull requests Codes accompanying the paper "Score Regularized Policy Optimization through Diffusion Behavior" (ICLR 2024). reinforcement-learning offline rl generative diffusion score-based-models d4rl srpo behavior-regularization Updated Feb 10, 2024 Python
hesoyam199x / SRPO Star 1 Code Issues Pull requests 🌟 Align diffusion processes with detailed human preferences to improve machine learning models for richer, more accurate outputs. reinforcement-learning offline animation popup rl alertview generative super-resolution actionsheet diffusion pose-estimation camera-pose-estimation score-based-models d4rl two-view-geometry srpo behavior-regularization eccv2024 Updated Nov 10, 2025 Python