İki taraflı müzakere için aktör-kritik pekiştirmeli öğrenme yaklaşımı

Designing an effective and intelligent bidding strategy is one of the most compelling research challenges in automated negotiation, where software agents negotiate with each other to find a mutual agreement when there is a conflict of interests. Instead of designing a hand-crafted decision-making module, this thesis proposes a novel bidding strategy adopting an actor-critic reinforcement learning approach, which learns what to offer in a bilateral negotiation. An entropy reinforcement learning framework called \acrfull{sac} is applied to the bidding problem, and a self-play approach is employed to train the model determining the target utility of the coming offer based on previous offer exchanges and remaining time. Furthermore, an imitation learning approach called behavior cloning is adopted to speed up the learning process. Also, a novel reward function is introduced that does not only take the agent's own utility, but also the opponent's utility at the end of the negotiation. The developed agent is empirically evaluated. Thus, a large number of negotiation sessions are run against a variety of opponents selected in different domains varying in size and opposition. The agent's performance is compared with its opponents and the performance of the baseline agents negotiating with the same opponents. The empirical results show that our agent successfully negotiates against challenging opponents in different negotiation scenarios without requiring any former information about the opponent or domain in advance. Furthermore, it achieves better results than the baseline agents regarding the received utility at the end of the successful negotiations.