Offline Reinforcement Learning Via Optimal Transport And Improved Performance Difference Theorem.

Boyi Wang Kai Lin Guohan Sun

Published in: ICTAI (2023)

Keyphrases

reinforcement learning
dynamic programming
multi agent
optimal solution
learning process
markov decision processes
optimal control
real time
data sets
data mining
machine learning
learning algorithm
worst case
optimal strategy
optimal design
transition model