Diffusion Spectral Representation for Reinforcement Learning.
Dmitry ShribakChen-Xiao GaoYitong LiChenjun XiaoBo DaiPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- dynamic programming
- markov decision processes
- spectral decomposition
- function approximation
- optimal policy
- state space
- multiscale
- model free
- learning process
- supervised learning
- clustering algorithm
- learning algorithm
- anisotropic diffusion
- diffusion process
- long run
- representation scheme
- spectral analysis
- hyperspectral imagery
- diffusion processes
- machine learning