Mean Field Equilibrium in Multi-Armed Bandit Game with Continuous Reward.
Xiong WangRiheng JiaPublished in: IJCAI (2021)
Keyphrases
- multi armed bandit
- nash equilibrium
- game theory
- multi armed bandits
- nash equilibria
- reinforcement learning
- games with incomplete information
- decentralized decision making
- markov random field
- repeated games
- mixed strategy
- correlated equilibrium
- resource allocation
- stochastic games
- closed form
- multi agent
- bayesian inference
- regret bounds
- bayesian networks
- state space
- markov decision processes
- model selection
- em algorithm