{"125721":{"#nid":"125721","#data":{"type":"event","title":"Ph.D. Thesis Proposal: Christopher Simpkins","body":[{"value":"\u003Cp\u003EPh.D. Thesis Proposal Announcement\u003Cbr \/\u003E\u003Cbr \/\u003ETitle: \u003Cstrong\u003EIntegrating Reinforcement Learning into a Programming Language\u003C\/strong\u003E\u003Cbr \/\u003E\u003Cbr \/\u003EChristopher Simpkins\u003Cbr \/\u003ESchool of Interactive Computing\u003Cbr \/\u003EGeorgia Institute of Technology\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EDate:\u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp;\u003Cstrong\u003E 8 May 2012\u003C\/strong\u003E (revised)\u003Cbr \/\u003ETime:\u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp; \u003Cstrong\u003E1:00 - 3:00 pm\u003C\/strong\u003E (revised)\u003Cbr \/\u003ELocation: \u003Cstrong\u003EKlaus 1116W\u003C\/strong\u003E (revised)\u003C\/p\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003Cstrong\u003ECommittee:\u003C\/strong\u003E\u003C\/p\u003E\u003Cul\u003E\u003Cli\u003EProfessor Charles Isbell, School of Interactive Computing (Advisor)\u003C\/li\u003E\u003Cli\u003EDr. Douglas Bodner, Tennenbaum Institute Professor\u003C\/li\u003E\u003Cli\u003EMark Riedl, School of Interactive Computing\u003C\/li\u003E\u003Cli\u003EDr. Spencer Rugaber, School of Computer Science\u003C\/li\u003E\u003Cli\u003EProfessor Andrea Thomaz, School of Interactive Computing\u003C\/li\u003E\u003C\/ul\u003E\u003Cp\u003E\u003Cbr \/\u003E\u003Cstrong\u003EAbstract:\u003C\/strong\u003E\u003Cbr \/\u003EMy Thesis: Integrating modular reinforcement learning (MRL) into a programming language supports adaptive agent software engineering. There are three claims implied in this thesis statement: (1) there is a such thing as MRL in a software engineering sense, (2) integrating MRL into a programming language is feasible, and (3) integrating MRL into a programming language is useful to software engineers writing adaptive software agents.\u003Cbr \/\u003E\u003Cbr \/\u003EModular reinforcement learning decomposes a reinforcement learning agent into components that solve subproblems of the total problem faced by an agent.\u0026nbsp; Hierarchical reinforcement learning (HRL), which decomposes problems temporally into subtasks, is well developed.\u0026nbsp; MRL, which decomposes problems into concurrent subproblems, is still nascent.\u0026nbsp; Existing approaches to MRL are not modular in a software engineering sense because inter-component reward coupling prevents reuse.\u0026nbsp; This dissertation will demonstrate the reward coupling problem and contribute a solution in the form of a reformulation of MRL and an algorithm that implements it.\u003Cbr \/\u003E\u003Cbr \/\u003EOur goal is to support practical software engineering.\u0026nbsp; The best way to support software engineering is with practical, usable programming languages.\u0026nbsp; This dissertation will contribute a programming language, implemented as a Scala library and asosciated idioms and design patterns, called AFABL -- A {Friendly|Flexible} Adaptive Behavior Language -- that integrates MRL, making MRL useful to software engineers writing practical adaptive agent software.\u003Cbr \/\u003E\u003Cbr \/\u003EFinally, we will apply AFABL to non-player character (NPC) programming in games and agent simulations to demonstrate its usefulness to software engineers writing adaptive software agents.\u0026nbsp; This application of AFABL to practical software engineering problems will distinguish AFABL from previous work in integrating RL into programming languages such as ALisp.\u003C\/p\u003E","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Integrating Reinforcement Learning into a Programming Language"}],"uid":"1","created_gmt":"2012-04-23 11:14:34","changed_gmt":"2016-10-08 01:58:45","author":"Jupiter","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2012-05-08T18:00:00-04:00","event_time_end":"2012-05-08T20:00:00-04:00","event_time_end_last":"2012-05-08T20:00:00-04:00","gmt_time_start":"2012-05-08 22:00:00","gmt_time_end":"2012-05-09 00:00:00","gmt_time_end_last":"2012-05-09 00:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"47223","name":"College of Computing"},{"id":"50876","name":"School of Interactive Computing"}],"categories":[],"keywords":[],"core_research_areas":[],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003E\u003Ca href=\u0022mailto:chris.simpkins@gatech.edu\u0022\u003EChristopher Simpkins\u003C\/a\u003E\u003C\/p\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}