Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning.
Xu-Hui LiuTian-Shuo LiuShengyi JiangRuifeng ChenZhilong ZhangXinwei ChenYang YuPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- real time
- online learning
- anisotropic diffusion
- function approximation
- energy consumption
- machine learning
- learning algorithm
- diffusion process
- parameter space
- state space
- markov decision process
- learning process
- sampling algorithm
- model free
- batch mode
- online environment
- diffusion processes
- learning problems
- monte carlo
- dynamic programming
- learning environment
- multi agent
- multiscale