{"id":{"repo_id":"harvard","oai_identifier":"oai:dash.harvard.edu:1/42719543"},"canonical_url":"https://search.dev.ndltd.org/etd/harvard/oai:dash.harvard.edu:1/42719543","repository":{"repo_id":"harvard","name":"Harvard University","base_url":"https://dash.harvard.edu/server/oai/request"},"display":{"title":"An Introduction to Reinforcement Learning","abstract":"This thesis presents a new course textbook on reinforcement learning (RL) with a focus on algorithms and their properties. The textbook is suitable for a one-semester introductory undergraduate course on RL for students with prior experience in basic probability, linear algebra, and multivariable calculus. We systematically cover the fundamentals of Markov decision processes, optimal control, multi-armed bandits, fitted dynamic programming algorithms, policy gradient methods, imitation learning, and tree search-based planning methods. Our contribution to the RL literature is an approachable and concise presentation of core RL algorithms that balances practical considerations with theoretical rigour. Each chapter includes extensive bibliographic notes that survey recent advances. We hope this textbook will equip the reader with a workable mental model for navigating modern RL research.","abstract_html":"This thesis presents a new course textbook on reinforcement learning (RL) with a focus on algorithms and their properties. The textbook is suitable for a one-semester introductory undergraduate course on RL for students with prior experience in basic probability, linear algebra, and multivariable calculus. We systematically cover the fundamentals of Markov decision processes, optimal control, multi-armed bandits, fitted dynamic programming algorithms, policy gradient methods, imitation learning, and tree search-based planning methods. Our contribution to the RL literature is an approachable and concise presentation of core RL algorithms that balances practical considerations with theoretical rigour. Each chapter includes extensive bibliographic notes that survey recent advances. We hope this textbook will equip the reader with a workable mental model for navigating modern RL research.","abstract_has_math":false,"creators":["Cai, Alexander Dazhen"],"institution":"Harvard University Engineering and Applied Sciences","degree_name":null,"degree_level":"Bachelor's","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Janson, Lucas"],"committee_chairs":[],"committee_members":["Janson, Lucas","Kakade, Sham M"],"year":2025,"date_issued":"2025-05-16","date_published":"2025-05-16","updated_at":"2026-07-27T19:55:49Z","subjects":["artificial intelligence","machine learning","Markov decision process","multi-armed bandits","optimal control","reinforcement learning","Statistics","Computer science"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["31931965"],"render_values":[{"text":"31931965","href":null,"code":true}]}]},"links":{"outbound_url":"https://dash.harvard.edu/handle/1/42719543","outbound_label":"Repository record","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Janson, Lucas"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Janson, Lucas","Kakade, Sham M"]},{"key":"dc:creator","label":"Author","values":["Cai, Alexander Dazhen"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-09-18T04:32:32Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-09-18T04:32:30Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-05-16"]},{"key":"dc:type","label":"Dc Type","values":["Thesis or Dissertation"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Bachelor's","Undergraduate"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Harvard University Engineering and Applied Sciences"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["artificial intelligence","machine learning","Markov decision process","multi-armed bandits","optimal control","reinforcement learning","Statistics","Computer science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["31931965"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://dash.harvard.edu/handle/1/42719543"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This thesis presents a new course textbook on reinforcement learning (RL) with a focus on algorithms and their properties. The textbook is suitable for a one-semester introductory undergraduate course on RL for students with prior experience in basic probability, linear algebra, and multivariable calculus. We systematically cover the fundamentals of Markov decision processes, optimal control, multi-armed bandits, fitted dynamic programming algorithms, policy gradient methods, imitation learning, and tree search-based planning methods. Our contribution to the RL literature is an approachable and concise presentation of core RL algorithms that balances practical considerations with theoretical rigour. Each chapter includes extensive bibliographic notes that survey recent advances. We hope this textbook will equip the reader with a workable mental model for navigating modern RL research."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["An Introduction to Reinforcement Learning"]}]}],"canonical_facts":{"dc:contributor.advisor":["Janson, Lucas"],"dc:contributor.committeemember":["Janson, Lucas","Kakade, Sham M"],"dc:creator":["Cai, Alexander Dazhen"],"dc:date.accessioned":["2025-09-18T04:32:32Z"],"dc:date.available":["2025-09-18T04:32:30Z"],"dc:date.issued":["2025-05-16"],"dc:description.abstract":["This thesis presents a new course textbook on reinforcement learning (RL) with a focus on algorithms and their properties. The textbook is suitable for a one-semester introductory undergraduate course on RL for students with prior experience in basic probability, linear algebra, and multivariable calculus. We systematically cover the fundamentals of Markov decision processes, optimal control, multi-armed bandits, fitted dynamic programming algorithms, policy gradient methods, imitation learning, and tree search-based planning methods. Our contribution to the RL literature is an approachable and concise presentation of core RL algorithms that balances practical considerations with theoretical rigour. Each chapter includes extensive bibliographic notes that survey recent advances. We hope this textbook will equip the reader with a workable mental model for navigating modern RL research."],"dc:format.mimetype":["application/pdf"],"dc:identifier.other":["31931965"],"dc:identifier.uri":["https://dash.harvard.edu/handle/1/42719543"],"dc:language.iso":["en"],"dc:subject":["artificial intelligence","machine learning","Markov decision process","multi-armed bandits","optimal control","reinforcement learning","Statistics","Computer science"],"dc:title":["An Introduction to Reinforcement Learning"],"dc:type":["Thesis or Dissertation"],"thesis:degree_level":["Bachelor's","Undergraduate"],"thesis:institution_name":["Harvard University Engineering and Applied Sciences"]},"updated_at":"2026-07-27T19:55:49Z"}