Cancellation-Free Regret Bounds for Lagrangian Approaches in Constrained Markov Decision Processes.

Adrian Müller Pragnya Alatur Giorgia Ramponi Niao He

Published in: CoRR (2023)

Keyphrases

markov decision processes
state space
finite state
dynamic programming
optimal policy
reinforcement learning
transition matrices
decision theoretic planning
policy iteration
optimal solution
infinite horizon
action sets
computational complexity
average reward