My Fair Bandit: Distributed Learning of Max-Min Fairness with Multi-player Bandits.
Ilai BistritzTavor Z. BaharavAmir LeshemNicholas BambosPublished in: CoRR (2020)
Keyphrases
- distributed learning
- max min
- multi player
- multi armed bandit
- regret bounds
- game playing
- online game
- min max
- educational games
- reinforcement learning
- collaborative learning
- game theory
- game play
- lower bound
- solution concepts
- resource allocation
- robust optimization
- hill climbing
- online learning
- role playing game
- multi agent
- cooperative
- knowledge integration
- mathematical programming
- linear programming
- learning environment