Partner-Aware Algorithms in Decentralized Cooperative Bandit Teams.
Erdem BiyikAnusha LalithaRajarshi SahaAndrea GoldsmithDorsa SadighPublished in: AAAI (2022)
Keyphrases
- cooperative
- multi agent
- theoretical analysis
- significant improvement
- decision making
- data structure
- learning algorithm
- recently developed
- active learning
- orders of magnitude
- computationally efficient
- coevolutionary algorithm
- benchmark datasets
- markov chain
- worst case
- least squares
- computational cost
- multi agent systems
- search algorithm