Learning pareto optimal solution of a multi-attribute bilateral negotiation using deep reinforcement

作者：

Highlights：

• The agent learns to decide in a multi-attribute negotiation via Deep Reinforcement.

• The buyer (learner) recognizes the sellers type online using K-means clustering.

• A mediator excludes the unreasonable offers from the feasible set of the offers.

• The existence and the uniqueness of the Nash Bargaining Solution are proven.

• The Bargaining Power of agents is examined.

摘要

•The agent learns to decide in a multi-attribute negotiation via Deep Reinforcement.•The buyer (learner) recognizes the sellers type online using K-means clustering.•A mediator excludes the unreasonable offers from the feasible set of the offers.•The existence and the uniqueness of the Nash Bargaining Solution are proven.•The Bargaining Power of agents is examined.

论文关键词：Multi-attribute negotiation,Deep auto encoder,Actor-critic,Nash bargaining solution,Bargaining power

论文评审过程：Received 25 November 2019, Revised 6 June 2020, Accepted 12 June 2020, Available online 18 June 2020, Version of Record 30 July 2020.

论文官网地址：https://doi.org/10.1016/j.elerap.2020.100987