Identifying useful subgoals in reinforcement learning by local graph partitioning.
Özgür SimsekAlicia P. WolfeAndrew G. BartoPublished in: ICML (2005)
Keyphrases
- graph partitioning
- reinforcement learning
- graph model
- image segmentation
- partitioning algorithm
- weighted graph
- clustering algorithm
- normalized cut
- spectral graph
- spectral clustering
- learning algorithm
- data clustering
- state space
- max cut
- spectral graph partitioning
- data objects
- superpixels
- machine learning
- shortest path
- denoising
- min cut
- similarity measure