[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117056-en":3,"doc-seo-117056-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},117056,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Understanding the Brain using Machine Learning - Enhancing Machine Learning with Neuroscience - Dissertation","This dissertation investigates how machine learning can be enhanced by insights from neuroscience to improve learning and decision-making. It develops neuromodulated reinforcement learning approaches for robot and self-driving navigation, including models of neuromodulated patience and adaptation under environment changes. It further proposes latent unified state representations for domain adaptation and introduces policy distillation with selective input gradient regularization to achieve efficient interpretability while maintaining performance and robustness.","UC Irvine  \nUC Irvine Electronic Theses and Dissertations  \nTitle  \nUnderstanding the Brain using Machine Learning and Enhancing Machine Learning with Neuroscience  \nPermalink  \n[https://escholarship.org/uc/item/3w0458n7](https://escholarship.org/uc/item/3w0458n7)  \nAuthor  \nXing, Jinwei  \nPublication Date  \n2023  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nUNIVERSITY OF CALIFORNIA,  \nIRVINE  \nUnderstanding the Brain using Machine Learning and Enhancing Machine Learning with  \nNeuroscience  \nDISSERTATION  \nsubmitted in partial satisfaction of the requirements for the degree of  \nDOCTOR OF PHILOSOPHY  \nin Cognitive Sciences  \nby  \nJinwei Xing  \nDissertation Committee:  \nProfessor Jeffrey L. Krichmar, Chair Assistant Professor Aaron Bornstein Associate Professor Sameer Singh  \n© 2023 Jinwei Xing  \nTABLE OF CONTENTS  \nPage  \nLIST OF FIGURES v  \nLIST OF TABLES xi  \nLIST OF ALGORITHMS xii  \nACKNOWLEDGMENTS xiii  \nVITA xiv  \nABSTRACT OF THE DISSERTATION xvi  \n1 Introduction 1  \n2 Background 4  \n2.1 Reinforcement Learning ............................. 4  \n2.2 Neuromodulation ................................. 6  \n2.3 Attention ..................................... 8  \n2.4 Generative Modeling ............................... 9  \n3 Neuromodulated Patience for Robot and Self-Driving Vehicle Navigation 11  \n3.1 Introduction .................................... 11  \n3.2 Methods ...................................... 13  \n3.2.1 Navigation Task .............................. 13  \n3.2.2 Robot and Software Design ....................... 14  \n3.2.3 Waypoint Navigation and Model of Neuromodulated Patience .... 16  \n3.2.4 Road Following with Deep Reinforcement Learning .......... 17  \n3.3 Results ....................................... 23  \n3.3.1 Waypoint Navigation in Encinitas Community park .......... 24  \n3.3.2 Waypoint Navigation in Aldrich park .................. 27  \n3.4 Discussion ..................................... 28  \n4 Adapting to Environment Changes Through Neuromodulation of Reinforcement Learning 30  \n4.1 Introduction .................................... 30  \n4.2 Problem ...................................... 32  \n4.3 Method ...................................... 33  \n4.3.1 ACh and NE Neuromodulation ..................... 33  \n4.3.2 Update of ACh and NE System ..................... 35  \n4.3.3 The Complete System .......................... 37  \n4.4 Experiments .................................... 37  \n4.5 Results ....................................... 41  \n4.5.1 Reinforcement Learning Performance .................. 41  \n4.5.2 Activity of Neuromodulatory System .................. 43  \n4.6 Conclusion ..................................... 44  \n5 Domain Adaptation in Reinforcement Learning via Latent Unified State Representation 45  \n5.1 Introduction .................................... 45  \n5.2 Related Work ................................... 47  \n5.3 Domain Adaptation in Reinforcement Learning ................ 49  \n5.4 Methods ...................................... 50  \n5.4.1 LUSR Definition ............................. 51  \n5.4.2 Learning LUSR .............................. 52  \n5.5 Experiments .................................... 54  \n5.5.1 CarRacing ................................. 54  \n5.5.2 Autonomous Driving in CARLA ..................... 56  \n5.6 Results and Discussion .............................. 57  \n5.6.1 CarRacing ................................. 57  \n5.6.2 Autonomous Driving in CARLA ..................... 62  \n5.7 Conclusion ..................................... 65  \n6 Achieving Efficient Interpretability of Reinforcement Learning via Policy Distillation and Selective Input Gradient Regularization 66  \n6.1 Introduction .................................... 66  \n6.2 Background and Motivation ........................... 68  \n6.2.1 Policy Distillation ............................. 68  \n6.2.2 Saliency Map in RL ..........","cbCailWv2b8noNRs","https://ap.wps.com/l/cbCailWv2b8noNRs","pdf",47772652,1,148,"English","en",105,"# Introduction\n# Background\n## Reinforcement Learning\n## Neuromodulation\n## Attention\n## Generative Modeling\n# Neuromodulated Patience for Robot and Self-Driving Vehicle Navigation\n# Adapting to Environment Changes Through Neuromodulation of Reinforcement Learning\n# Domain Adaptation in Reinforcement Learning via Latent Unified State Representation\n# Achieving Efficient Interpretability of Reinforcement Learning via Policy Distillation and Selective Input Gradient Regularization\n# Linking Global Top-Down Views to First-Person Views in the Brain\n# Conclusions","[{\"question\":\"What is the dissertation’s main theme?\",\"answer\":\"The dissertation focuses on understanding the brain using machine learning and enhancing machine learning with neuroscience by integrating neurobiological mechanisms into learning and navigation systems.\"},{\"question\":\"How does it improve robot or self-driving navigation?\",\"answer\":\"It introduces a neuromodulated patience approach combined with deep reinforcement learning for waypoint navigation and road following, then evaluates results in robot-related environments.\"},{\"question\":\"What methods are proposed for adaptation and interpretability?\",\"answer\":\"It proposes latent unified state representation for domain adaptation in reinforcement learning, and it uses policy distillation with selective input gradient regularization to obtain more efficient interpretability while preserving performance and robustness.\"}]","Understanding the Brain using Machine Learning - Enhancing Machine Learning with Neuroscience - Dissertation | PDF",1785673474,373,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"understanding-the-brain-using-machine-learning-enhancing-machine-learning-with-neuroscience-dissertation","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/understanding-the-brain-using-machine-learning-enhancing-machine-learning-with-neuroscience-dissertation/117056/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the dissertation’s main theme?","Question",{"text":75,"@type":76},"The dissertation focuses on understanding the brain using machine learning and enhancing machine learning with neuroscience by integrating neurobiological mechanisms into learning and navigation systems.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does it improve robot or self-driving navigation?",{"text":80,"@type":76},"It introduces a neuromodulated patience approach combined with deep reinforcement learning for waypoint navigation and road following, then evaluates results in robot-related environments.",{"name":82,"@type":73,"acceptedAnswer":83},"What methods are proposed for adaptation and interpretability?",{"text":84,"@type":76},"It proposes latent unified state representation for domain adaptation in reinforcement learning, and it uses policy distillation with selective input gradient regularization to obtain more efficient interpretability while preserving performance and robustness.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]