In order to enhance the efficiency in bilateral multi-issue negotiation under incomplete information, double learning algorithm that includes Q-learning algorithm and Bayesian learning algorithm is presented. The Q-le...In order to enhance the efficiency in bilateral multi-issue negotiation under incomplete information, double learning algorithm that includes Q-learning algorithm and Bayesian learning algorithm is presented. The Q-learning algorithm is used to learn the weights of issues, and the Bayesian learning algorithm is used to learn the reservation price of issues. Experiments show that the algorithm can help agents to negotiate more efficiently.展开更多
基金by the Ministerial Level Advanced Foundation(41325081)
文摘In order to enhance the efficiency in bilateral multi-issue negotiation under incomplete information, double learning algorithm that includes Q-learning algorithm and Bayesian learning algorithm is presented. The Q-learning algorithm is used to learn the weights of issues, and the Bayesian learning algorithm is used to learn the reservation price of issues. Experiments show that the algorithm can help agents to negotiate more efficiently.
