Proposal of Detour Path Suppression Method in PS Reinforcement Learning and Its Application to Altruistic Multi-agent Environment.
Daisuke ShiraishiKazuteru MiyazakiHiroaki KobayashiPublished in: PRIMA (2018)
Keyphrases
- reinforcement learning
- high accuracy
- detection method
- cost function
- computational cost
- multi agent environment
- clustering method
- similarity measure
- objective function
- cooperative
- preprocessing
- image segmentation
- edge detection
- policy search
- transition model
- optimal path
- genetic algorithm ga
- support vector machine svm
- support vector machine
- dynamic programming
- pairwise