Multi-armed bandits
9 methods in the atlas attack this one problem. They are rivals: each wins something the others do not.
Phrasings that mean this problem
Multi-armed banditsAdversarial banditsContextual banditsExploration in recommendationPure-exploration bandits
game-search
- Sequential halvingBudget-splitting arm eliminationspecialistgame-search
machine-learning
- Upper confidence boundstandalonecanonmachine-learning
- Thompson samplingPosterior drawscanonfull lesson ▸machine-learning
- Epsilon-greedyFixed exploration ratecanonmachine-learning
- Greedy banditAlways play the current leaderspecialistmachine-learning
- Uniform allocationEqual pulls per armspecialistmachine-learning
- EXP3Exponential-weight explorationstandardmachine-learning
- LinUCBRidge-confidence bonusstandardmachine-learning
recommender-causal
- Multi-armed bandit recommendationThompson samplingstandardrecommender-causal