A Primal-Dual-Critic Algorithm for Offline Constrained Reinforcement Learning.

Kihyuk Hong Yuhang Li Ambuj Tewari

Published in: CoRR (2023)

Keyphrases

primal dual
linear programming
reinforcement learning
convergence rate
computational complexity
learning algorithm
optimal solution
dynamic programming
affine scaling
simplex method
randomly generated
linear program
np hard
convex hull
linear programming problems
saddle point
dual formulation
pairwise