Policy-based Primal-Dual Methods for Convex Constrained Markov Decision Processes.
Donghao YingMengzi GuoYuhao DingJavad LavaeiZuo-Jun ShenPublished in: CoRR (2022)
Keyphrases
- markov decision processes
- optimal policy
- primal dual
- convex optimization
- dynamic programming
- convex optimization problems
- state space
- finite horizon
- infinite horizon
- linear programming
- approximation algorithms
- linear program
- finite state
- reward function
- average cost
- linear programming problems
- partially observable
- policy iteration
- image restoration
- action space
- saddle point
- algorithm for linear programming