DSpace Repository

Solving Interleaved and Blended Sequential Decision-Making Problems through Modular Neuroevolution

Show simple item record

dc.contributor.author Schrum, Jacob
dc.contributor.author Miikkulainen, Risto
dc.date.accessioned 2016-12-14T16:19:57Z
dc.date.available 2016-12-14T16:19:57Z
dc.date.issued 2015
dc.identifier.citation Schrum, J., & Miikkulainen, R. (2015). Solving Interleaved and Blended Sequential Decision-Making Problems Through Modular Neuroevolution. In Proceedings of the 2015 Annual Conference on Genetic and Evolutionary Computation (pp. 345–352). New York, NY, USA: ACM. https://doi.org/10.1145/2739480.2754744 en_US
dc.identifier.uri http://hdl.handle.net/11214/155
dc.description This is an Accepted Manuscript of an article published by ACM. Schrum, J., & Miikkulainen, R. (2015). Solving Interleaved and Blended Sequential Decision-Making Problems Through Modular Neuroevolution. In Proceedings of the 2015 Annual Conference on Genetic and Evolutionary Computation (pp. 345–352). New York, NY, USA: ACM. https://doi.org/10.1145/2739480.2754744 en_US
dc.description.abstract Many challenging sequential decision-making problems require agents to master multiple tasks, such as defense and offense in many games. Learning algorithms thus benefit from having separate policies for these tasks, and from knowing when each one is appropriate. How well the methods work depends on the nature of the tasks: Interleaved tasks are disjoint and have different semantics, whereas blended tasks have regions where semantics from different tasks overlap. While many methods work well in interleaved tasks, blended tasks are difficult for methods with strict, human-specified task divisions, such as Multitask Learning. In such problems, task divisions should be discovered automatically. To demonstrate the power of this approach, the MM-NEAT neuroevolution framework is applied in this paper to two variants of the challenging video game of Ms. Pac-Man. In the simplified interleaved version of the game, the results demonstrate when and why such machine-discovered task divisions are useful. In the standard blended version of the game, a surprising, highly effective machine-discovered task division surpasses human-specified divisions, achieving the best scores to date in this game. Modular neuroevolution is thus a promising technique for discovering multimodal behavior for challenging real-world tasks. en_US
dc.language.iso en_US en_US
dc.publisher ACM en_US
dc.subject Neuroevolution en_US
dc.subject Computer games en_US
dc.subject Modular neuroevolution en_US
dc.title Solving Interleaved and Blended Sequential Decision-Making Problems through Modular Neuroevolution en_US
dc.type Article en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search


Browse

My Account

Links