Symbolic method for deriving policy in reinforcement learning.
Eduard AlibekovJirí KubalíkRobert BabuskaPublished in: CDC (2016)
Keyphrases
- reinforcement learning
- high precision
- classification method
- detection method
- high accuracy
- dynamic programming
- similarity measure
- optimal policy
- support vector machine
- computational cost
- experimental evaluation
- significant improvement
- pairwise
- preprocessing
- cost function
- prior knowledge
- image sequences
- function approximation