Better Rates for Any Adversarial Deterministic MDP.

Ofer Dekel Elad Hazan

Published in: ICML (3) (2013)

Keyphrases

markov decision processes
reinforcement learning
optimal policy
multi agent
utility function
markov decision process
state space
linear program
finite state
dynamic programming algorithms
linear programming
data sets
dynamic programming
black box
decision theoretic
relaxation algorithm