Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations.
Angeliki KamoutsiGoran BanjacJohn LygerosPublished in: CoRR (2021)
Keyphrases
- primal dual
- reinforcement learning
- linear program
- affine scaling
- linear programming
- semidefinite programming
- lower bound
- approximation algorithms
- convergence rate
- convex optimization
- interior point methods
- simplex algorithm
- algorithm for linear programming
- upper bound
- duality gap
- simplex method
- learning algorithm
- special case
- variational inequalities
- objective function
- interior point
- computer vision