Thompson Sampling for Factored Multi-Agent Bandits.
Timothy VerstraetenEugenio BargiacchiPieter J. K. LibinDiederik M. RoijersAnn NowéPublished in: CoRR (2019)
Keyphrases
- multi agent
- state space
- multiagent systems
- reinforcement learning
- multi agent systems
- monte carlo
- multi armed bandit
- intelligent agents
- stochastic systems
- sampling strategies
- cooperative
- multiple agents
- agent communication
- multi armed bandits
- machine learning
- agent based simulations
- sampled data
- agent oriented
- sampling algorithm
- random sampling
- autonomous agents