On the Minimax Regret for Linear Bandits in a wide variety of Action Spaces.

Debangshu Banerjee Aditya Gopalan

Published in: CoRR (2023)

Keyphrases

minimax regret
action space
state space
preference elicitation
markov decision processes
decision problems
real valued
utility function
markov chain
stochastic processes
objective function
action selection
stochastic programming