Proximal Reinforcement Learning: A New Theory of Sequential Decision Making in Primal-Dual Spaces.
Sridhar MahadevanBo LiuPhilip S. ThomasWilliam DabneyStephen GiguereNicholas JacekIan GempJi LiuPublished in: CoRR (2014)
Keyphrases
- sequential decision making
- reinforcement learning
- primal dual
- linear programming
- affine scaling
- convex optimization
- linear program
- temporal difference
- interior point methods
- convergence rate
- state space
- approximation algorithms
- algorithm for linear programming
- linear programming problems
- reinforcement learning algorithms
- interior point algorithm
- decision problems
- function approximation
- dynamic programming
- influence diagrams
- markov decision processes
- simplex algorithm
- model free
- multi agent
- machine learning
- belief functions
- multiresolution
- image processing
- graphical models
- supervised learning
- learning algorithm