Fast Bellman Updates for Wasserstein Distributionally Robust MDPs.

Zhuodong Yu Ling Dai Shaohang Xu Siyang Gao Chin Pang Ho

Published in: NeurIPS (2023)

Keyphrases

markov decision processes
robust optimization
reinforcement learning
dynamic programming
computationally efficient
data sets
linear program
pointwise
machine learning
state space
sufficient conditions
multistage
piecewise linear