Entangled photons for competitive multi-armed bandit problem: achievement of maximum social reward, equality, and deception prevention.
Makoto NaruseNicolas ChauvetDavid JegousoBenoit BoulangerHayato SaigoKazuya OkamuraHirokazu HoriAurélien DrezetSerge HuantGuillaume BachelierPublished in: CoRR (2018)
Keyphrases
- social interaction
- social media
- social networks
- reinforcement learning
- incomplete information
- multi armed bandit
- social context
- collective intelligence
- deception detection
- total reward
- long run
- maximum number
- information systems
- social networking sites
- social behavior
- learning community
- social networking
- database systems