A Primal-Dual-Critic Algorithm for Offline Constrained Reinforcement Learning.
Kihyuk HongYuhang LiAmbuj TewariPublished in: AISTATS (2024)
Keyphrases
- primal dual
- linear programming
- np hard
- dynamic programming
- reinforcement learning
- learning algorithm
- computational complexity
- approximation algorithms
- optimal solution
- search direction
- worst case
- linear program
- simplex algorithm
- convergence rate
- semidefinite programming
- randomly generated
- linear programming problems
- interior point algorithm
- interior point
- saddle point
- simplex method
- iterative algorithms
- convex optimization
- learning problems
- optimal policy
- state space
- image processing