Research on multi-agent collaborative hunting algorithm based on game theory and Q-learning for a single escaper.
Yanbin ZhengWenxin FanMengyun HanPublished in: J. Intell. Fuzzy Syst. (2021)
Keyphrases
- game theory
- multi agent
- learning algorithm
- dynamic programming
- fictitious play
- cooperative
- computational complexity
- worst case
- k means
- reinforcement learning
- single agent
- probabilistic model
- search space
- multi agent systems
- optimal solution
- state space
- upper bound
- expectation maximization
- monte carlo
- decision problems
- lower bound
- average case
- stochastic approximation
- human computation