A primal-dual perspective for distributed TD-learning.
Han-Dong LimDonghwan LeePublished in: CoRR (2023)
Keyphrases
- primal dual
- td learning
- linear programming
- convex optimization
- linear program
- affine scaling
- algorithm for linear programming
- interior point methods
- temporal difference
- convergence rate
- approximation algorithms
- evaluation function
- linear programming problems
- simplex algorithm
- interior point algorithm
- function approximation
- machine learning
- denoising
- np hard
- multi step
- reinforcement learning algorithms
- cost function
- multi objective
- multiscale
- genetic algorithm