{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/158922"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/158922","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"On Solving Larger Games: Designing New Algorithms Adaptable to Deep Reinforcement Learning","abstract":"In this thesis, we explore the design of algorithms capable of handling large games where the state space is too large to store strategies in a tabular format from a theoretical perspective. Specifically, we focus on developing algorithms suitable for deep reinforcement learning in two-player zero-sum extensive-form games. There are three critical properties for effective deep multi-agent reinforcement learning: (last/best) iterate convergence, efficient utilization of stochastic trajectory feedback, and theoretically sound avoidance of importance sampling corrections. Chapter 3 introduces Regularized Optimistic Mirror Descent (Reg-OMD), which provably converges to the Nash equilibrium (NE) linearly in last-iterate. Chapter 4 shows that algorithms based on regret decomposition enjoy best-iterate convergence to the NE. Chapter 5 proposes Q-value based Regret Minimization (QFR), which achieves all three properties simultaneously.","abstract_html":"In this thesis, we explore the design of algorithms capable of handling large games where the state space is too large to store strategies in a tabular format from a theoretical perspective. Specifically, we focus on developing algorithms suitable for deep reinforcement learning in two-player zero-sum extensive-form games. There are three critical properties for effective deep multi-agent reinforcement learning: (last/best) iterate convergence, efficient utilization of stochastic trajectory feedback, and theoretically sound avoidance of importance sampling corrections. Chapter 3 introduces Regularized Optimistic Mirror Descent (Reg-OMD), which provably converges to the Nash equilibrium (NE) linearly in last-iterate. Chapter 4 shows that algorithms based on regret decomposition enjoy best-iterate convergence to the NE. Chapter 5 proposes Q-value based Regret Minimization (QFR), which achieves all three properties simultaneously.","abstract_has_math":false,"creators":["Liu, Mingyang"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Ozdaglar, Asuman","Farina, Gabriele"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-02","date_published":"2025-02","updated_at":"2026-07-22T22:21:24Z","subjects":[],"languages":[],"rights":["Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)","Copyright retained by author(s)"],"rights_urls":["https://creativecommons.org/licenses/by-nc-nd/4.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/158922","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Ozdaglar, Asuman","Farina, Gabriele"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Liu, Mingyang"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-03-27T16:58:22Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-03-27T16:58:22Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-02"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Science in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://creativecommons.org/licenses/by-nc-nd/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/158922"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["In this thesis, we explore the design of algorithms capable of handling large games where the state space is too large to store strategies in a tabular format from a theoretical perspective. Specifically, we focus on developing algorithms suitable for deep reinforcement learning in two-player zero-sum extensive-form games. There are three critical properties for effective deep multi-agent reinforcement learning: (last/best) iterate convergence, efficient utilization of stochastic trajectory feedback, and theoretically sound avoidance of importance sampling corrections. Chapter 3 introduces Regularized Optimistic Mirror Descent (Reg-OMD), which provably converges to the Nash equilibrium (NE) linearly in last-iterate. Chapter 4 shows that algorithms based on regret decomposition enjoy best-iterate convergence to the NE. Chapter 5 proposes Q-value based Regret Minimization (QFR), which achieves all three properties simultaneously."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:title","label":"Title","values":["On Solving Larger Games: Designing New Algorithms Adaptable to Deep Reinforcement Learning"]}]}],"canonical_facts":{"dc:contributor.advisor":["Ozdaglar, Asuman","Farina, Gabriele"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Liu, Mingyang"],"dc:date.accessioned":["2025-03-27T16:58:22Z"],"dc:date.available":["2025-03-27T16:58:22Z"],"dc:date.issued":["2025-02"],"dc:description.abstract":["In this thesis, we explore the design of algorithms capable of handling large games where the state space is too large to store strategies in a tabular format from a theoretical perspective. Specifically, we focus on developing algorithms suitable for deep reinforcement learning in two-player zero-sum extensive-form games. There are three critical properties for effective deep multi-agent reinforcement learning: (last/best) iterate convergence, efficient utilization of stochastic trajectory feedback, and theoretically sound avoidance of importance sampling corrections. Chapter 3 introduces Regularized Optimistic Mirror Descent (Reg-OMD), which provably converges to the Nash equilibrium (NE) linearly in last-iterate. Chapter 4 shows that algorithms based on regret decomposition enjoy best-iterate convergence to the NE. Chapter 5 proposes Q-value based Regret Minimization (QFR), which achieves all three properties simultaneously."],"dc:description.degree":["S.M."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/158922"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)","Copyright retained by author(s)"],"dc:rights.uri":["https://creativecommons.org/licenses/by-nc-nd/4.0/"],"dc:title":["On Solving Larger Games: Designing New Algorithms Adaptable to Deep Reinforcement Learning"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Science in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:21:24Z"}