AINeutralarXiv – CS AI · 3h ago6/10
🧠
Diffusion-Augmented Markov Decision Processes for Maximum Entropy Reinforcement Learning
Researchers have developed Diffusion-Augmented Markov Decision Processes (DA-MDPs), a framework that integrates diffusion models into maximum entropy reinforcement learning to sample from optimal policy trajectory distributions. The approach is tested on three RL algorithms (PPO, WPO, REPPO) and demonstrates competitive or superior performance on continuous-control tasks while excelling at modeling multimodal action distributions.