Efficient Diffusion Policies for Offline Reinforcement Learning.

Bingyi Kang Xiao Ma Chao Du Tianyu Pang Shuicheng Yan

Published in: CoRR (2023)

Keyphrases

reinforcement learning
optimal policy
markov decision processes
real time
multiscale
data sets
computationally efficient
transfer learning
evaluation function
function approximation
reinforcement learning algorithms
fitted q iteration