Approximate Policy Iteration using Large-Margin Classifiers.
Michail G. LagoudakisRonald ParrPublished in: IJCAI (2003)
Keyphrases
- large margin classifiers
- approximate policy iteration
- reinforcement learning
- policy iteration
- support vector
- markov decision problems
- policy search
- multi class
- markov decision processes
- temporal difference
- maximum margin
- generalization bounds
- learning algorithm
- optimal policy
- soft margin
- multiple kernel learning
- model free
- cost sensitive
- linear programming
- least squares
- state space
- dynamic programming
- markov decision process
- kernel function
- support vector machine
- probability distribution
- convergence rate
- ranking algorithm
- learning problems
- reinforcement learning algorithms
- transfer learning