Print Email Facebook Twitter Training a Negotiating Agent through Self-Play Title Training a Negotiating Agent through Self-Play Author Jurševskis, Renāts (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Renting, B.M. (mentor) Murukannaiah, P.K. (mentor) Zhang, X. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2022-06-23 Abstract Recent developments in applying reinforcement learning to cooperative environments, like negotiation, have brought forward an important question: how well can a negotiating agent be trained through self-play? Previous research has seen successful application of self-play to other settings, like the games of chess and Go. This paper explores the usage of self-play within the training of a negotiating agent and determines if it is possible to successfully train an agent purely through self-play. The results of the experimentation show that a training stage using self-play can match or even exceed an approach using a set of training opponents. By using multiple self-play opponents, the average utility can be further improved by introducing more variance during training. In addition, using a combination of both self-play and training opponents leads to a hybrid approach that performs better than either of the two techniques separately. Subject negotiating agentsself-playreinforcement learning To reference this document use: http://resolver.tudelft.nl/uuid:4b1cc402-cb64-4c86-ac5b-6fcb891f8472 Part of collection Student theses Document type bachelor thesis Rights © 2022 Renāts Jurševskis Files PDF Research_Paper_2022.06.19_3.pdf 403.61 KB Close viewer /islandora/object/uuid:4b1cc402-cb64-4c86-ac5b-6fcb891f8472/datastream/OBJ/view