QMIMC: Q-Learning Model Based on Imperfect-information under Multi-agent Crowdtesting.
Jie ZhangKefan LiBaoming ZhangMing XuChongjun WangPublished in: ISPA/BDCloud/SocialCom/SustainCom (2021)
Keyphrases
- multi agent
- imperfect information
- reinforcement learning
- cooperative
- game theoretic
- model free
- game theory
- multi agent systems
- perfect information
- stochastic games
- imperfect information games
- game playing
- single agent
- card game
- multiagent systems
- game tree search
- alternating time temporal logic
- game tree
- multiple agents
- state space
- e learning
- finite automata
- reinforcement learning algorithms
- decision making
- decision problems
- hidden markov models