Policy Representation via Diffusion Probability Model for Reinforcement Learning.
Long YangZhixiong HuangFenghao LeiYucun ZhongYiming YangCong FangShiting WenBinbin ZhouZhouchen LinPublished in: CoRR (2023)
Keyphrases
- probability model
- reinforcement learning
- optimal policy
- statistical model
- probability distribution
- bit plane
- markov decision process
- action selection
- action space
- anisotropic diffusion
- policy search
- markov decision processes
- multi agent
- learning algorithm
- function approximation
- control problems
- image representation
- machine learning
- infinite horizon
- reinforcement learning algorithms
- decision problems
- approximate dynamic programming
- hypothesis test