Sampling Beats Fixed Estimate Predictors for Cloning Stochastic Behavior in Multiagent Systems.
Brian HrolenokByron BootsTucker Hybinette BalchPublished in: AAAI (2017)
Keyphrases
- multiagent systems
- multi agent
- monte carlo
- emergent behavior
- autonomous agents
- distributed artificial intelligence
- coalition formation
- multiagent architecture
- multiagent planning
- multi agent systems
- agent technology
- multiagent reinforcement learning
- human behavior
- trust model
- multiagent learning
- robotic soccer
- agent coordination
- learning algorithm
- complex systems
- learning agents
- decentralized control
- decision makers
- learning in multi agent systems