{"689549":{"#nid":"689549","#data":{"type":"event","title":"PhD Defense by Nathan B. Williams","body":[{"value":"\u003Cp\u003EStudent Name: Nathan B. Williams\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EAdvisor: Dr. Dimitri Mavris\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EMilestone: PhD Thesis Final Examination (Defense)\u003Cbr\u003E\u003Cbr\u003EDegree Program: Computational Science \u0026amp; Engineering (AE Home School)\u003Cbr\u003E\u003Cbr\u003ETitle: Graph-ReCon: A Graph-Based Framework for Induced Relational Context in Model-Free Reinforcement Learning\u003Cbr\u003E\u003Cbr\u003EAbstract: Model-Free Reinforcement Learning (RL) has shown incredible success across many fields, including automation, finance, and healthcare. However, despite these achievements, Model-Free RL agents continue to face two critical challenges that inhibit their utility: (1) the Performance Challenge, how well the agent works, characterized by poor sample efficiency, instability in training, and mediocre generalization; and (2) the Interpretability Challenge, how well the agent can be understood, as agents remain difficult to understand and explain to stakeholders. Thus, this dissertation is guided by a singular purpose \u2013 to advance Model-Free Reinforcement Learning by improving agent performance and interpretability. Although these challenges may seem distinct, they share a common dependency \u2013 the state representation, i.e., how the agent views and encodes its environment. State Representation Learning (SRL), a fundamental component of Model-Free RL, offers a variety of methods that seek to do just that \u2013 enhance the state representation. However, existing SRL approaches primarily focus on performance and do not explicitly address interpretability. Moreover, across SRL classes, there exists no unified approach that enables online, structured, relational state representation learning in a manner that is both environment-agnostic and algorithm-agnostic. This deficiency constitutes the central technical gap addressed in this work. To address this gap, this dissertation introduces Graph-ReCon: a graph-based framework for induced relational context in Model-Free RL. Graph-ReCon extends the traditional Model-Free RL pipeline by incorporating a Relational Context component, consisting of three core parts: (1) an experience graph that captures agent-environment interactions; (2) a Graph Neural Network (GNN) to process the experience graph; and (3) two auxiliary losses to further refine the state representation space. The Graph-ReCon framework is evaluated in two complementary parts. Part I, consisting of three experiments, demonstrates consistent improvements in sample efficiency, training stability, generalization, and interpretability across multiple environments and algorithms. Part II extends this evaluation to cybersecurity, highlighting Graph-ReCon\u2019s practical utility in a high-stakes domain. Collectively, these results demonstrate that incorporating relational context leads to more effective and more interpretable agents. Ultimately, this work is grounded in a simple, but elegant principle: decisions are important, but the relationships between decisions are no less important than the decisions themselves.\u003Cbr\u003E\u003Cbr\u003EDate and time: 2026-04-20, 12:30 p.m.\u003Cbr\u003E\u003Cbr\u003ELocation: Collaborative Visualization Environment (CoVE) Weber SST II\u003Cbr\u003E\u003Cbr\u003ECommittee:\u003Cbr\u003EDr. Dimitri Mavris (advisor), School of Aerospace Engineering\u003Cbr\u003EDr. Woong-Je Sung, School of\u0026nbsp;Aerospace Engineering\u003Cbr\u003EDr. Dalton Lin, Sam Nunn School of International\u0026nbsp;Affairs\u0026nbsp;\u003Cbr\u003EDr. Anqi Wu, School of Computational Science\u0026nbsp;and Engineering\u003Cbr\u003EDr. Xiuwei Zhang, School of Computational Science\u0026nbsp;and Engineering\u003Cbr\u003E,\u0026nbsp;\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EGraph-ReCon: A Graph-Based Framework for Induced Relational Context in Model-Free Reinforcement Learning\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Graph-ReCon: A Graph-Based Framework for Induced Relational Context in Model-Free Reinforcement Learning"}],"uid":"27707","created_gmt":"2026-04-07 20:48:53","changed_gmt":"2026-04-07 20:49:31","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2026-04-20T12:30:00-04:00","event_time_end":"2026-04-20T14:30:00-04:00","event_time_end_last":"2026-04-20T14:30:00-04:00","gmt_time_start":"2026-04-20 16:30:00","gmt_time_end":"2026-04-20 18:30:00","gmt_time_end_last":"2026-04-20 18:30:00","rrule":null,"timezone":"America\/New_York"},"location":"Collaborative Visualization Environment (CoVE) Weber SST II","extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"100811","name":"Phd Defense"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78771","name":"Public"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}