Login / Signup
Policy-Based Primal-Dual Methods for Convex Constrained Markov Decision Processes.
Donghao Ying
Mengzi Amy Guo
Yuhao Ding
Javad Lavaei
Zuo-Jun Max Shen
Published in:
AAAI (2023)
Keyphrases
</>
markov decision processes
optimal policy
primal dual
convex optimization
reinforcement learning
dynamic programming
linear programming
convex optimization problems
special case
state space
convergence rate
infinite horizon
average cost
interior point methods