Robust Reinforcement Learning Under Minimax Regret for Green Security.

Lily Xu Andrew Perrault Fei Fang Haipeng Chen Milind Tambe

Published in: CoRR (2021)

Keyphrases

reinforcement learning
minimax regret
learning algorithm
utility function
markov decision processes
dynamic programming
state space
multi class
transfer learning
learning tasks
preference elicitation