Decentralized Cooperative Stochastic Bandits.
David Martínez-RubioVarun KanadePatrick RebeschiniPublished in: NeurIPS (2019)
Keyphrases
- cooperative
- stochastic systems
- multi agent
- distributed problem solving
- regret bounds
- multi armed bandits
- multi armed bandit
- stochastic nature
- stochastic models
- game theory
- stochastic model
- learning automata
- cooperative learning
- cooperating agents
- digital libraries
- multi agent systems
- machine learning
- markov processes
- distributed systems
- fully distributed
- mobile robot
- multiagent reinforcement learning
- decentralized decision making