Data-Driven Inverse Reinforcement Learning for Expert-Learner Zero-Sum Games.

Wenqian Xue Bosen Lian Jialu Fan Tianyou Chai Frank L. Lewis

Published in: CoRR (2023)

Keyphrases

inverse reinforcement learning
data driven
bayesian nonparametric
partially observable environments
preference elicitation
temporal difference
reward function
learning process
reinforcement learning
multi agent
special case
mixture model
imperfect information