Adaptive Discretization for Adversarial Bandits with Continuous Action Spaces.

Chara Podimata Aleksandrs Slivkins

Published in: CoRR (2020)

Keyphrases

action space
state space
markov decision processes
continuous action
real valued
reinforcement learning
continuous state
state and action spaces
continuous state spaces
control policies
action selection
stochastic processes
skill learning
continuous variables
markov decision process
search space