Login / Signup
Finite-Time Complexity of Online Primal-Dual Natural Actor-Critic Algorithm for Constrained Markov Decision Processes.
Sihan Zeng
Thinh T. Doan
Justin Romberg
Published in:
CoRR (2021)
Keyphrases
</>
primal dual
markov decision processes
dynamic programming
linear programming
convergence rate
learning algorithm
worst case
state space
np hard
approximation algorithms
reinforcement learning
optimal policy
finite state
least squares
step size
objective function
natural actor critic