This dissertation presents a reinforcement learning-based approach to modeling and optimizing decision-making in professional basketball free agency and related economic environments. A Markov Decision Process (MDP) framework is introduced to capture the strategic interactions of NBA teams bidding for free agents under budgetary and roster constraints. To address computational scalability challenges, a reinforcement learning (RL) environment is developed, leveraging Proximal Policy Optimization (PPO) to approximate optimal policies for team decision-making.
Empirical results demonstrate that the RL agent successfully learns strategic bidding behavior that aligns with dynamic programming benchmarks in simplified settings while scaling effectively to larger, intractable environments. The study further extends reinforcement learning applications to a job scheduling problem, where an agent must allocate resources to maximize returns under uncertainty, and to a capacity-constrained Cournot market, where firms strategically invest to maximize long-term profitability.
Findings indicate that reinforcement learning serves as a powerful tool for approximating optimal strategies in complex, non-tractable markets. This work contributes to the growing intersection of computational economics, market design, and artificial intelligence by showcasing the effectiveness of reinforcement learning in decision-support systems for economic and strategic environments.
","abstract_html":"<p>This dissertation presents a reinforcement learning-based approach to modeling and optimizing decision-making in professional basketball free agency and related economic environments. A Markov Decision Process (MDP) framework is introduced to capture the strategic interactions of NBA teams bidding for free agents under budgetary and roster constraints. To address computational scalability challenges, a reinforcement learning (RL) environment is developed, leveraging Proximal Policy Optimization (PPO) to approximate optimal policies for team decision-making.</p> <p>Empirical results demonstrate that the RL agent successfully learns strategic bidding behavior that aligns with dynamic programming benchmarks in simplified settings while scaling effectively to larger, intractable environments. The study further extends reinforcement learning applications to a job scheduling problem, where an agent must allocate resources to maximize returns under uncertainty, and to a capacity-constrained Cournot market, where firms strategically invest to maximize long-term profitability.</p> <p>Findings indicate that reinforcement learning serves as a powerful tool for approximating optimal strategies in complex, non-tractable markets. This work contributes to the growing intersection of computational economics, market design, and artificial intelligence by showcasing the effectiveness of reinforcement learning in decision-support systems for economic and strategic environments.</p>","abstract_has_math":false,"creators":["Cohn, Jacob"],"institution":null,"degree_name":"Doctor of Philosophy (PhD)","degree_level":"Dissertation","degree_discipline":"Computational and Data Sciences","degree_department":null,"school":null,"contributors":["David Porter","Stephen Rassenti","Ryan French"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-05-01T07:00:00Z","date_published":"2025-05-01T07:00:00Z","updated_at":"2026-07-24T01:38:43Z","subjects":["Free Agency","Reinforcement Learning","Scheduling","Cournot","Dynamic Programming","Markets","Artificial Intelligence and Robotics","Behavioral Economics","Data Science","Design of Experiments and Sample Surveys","Labor Economics"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.chapman.edu/cads_dissertations/49","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["David Porter","Stephen Rassenti","Ryan French"]},{"key":"dc:creator","label":"Author","values":["Cohn, Jacob"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2026-05-09T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computational and Data Sciences"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy (PhD)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Free Agency","Reinforcement Learning","Scheduling","Cournot","Dynamic Programming","Markets","Artificial Intelligence and Robotics","Behavioral Economics","Data Science","Design of Experiments and Sample Surveys","Labor Economics"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.chapman.edu/cads_dissertations/49"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This dissertation presents a reinforcement learning-based approach to modeling and optimizing decision-making in professional basketball free agency and related economic environments. A Markov Decision Process (MDP) framework is introduced to capture the strategic interactions of NBA teams bidding for free agents under budgetary and roster constraints. To address computational scalability challenges, a reinforcement learning (RL) environment is developed, leveraging Proximal Policy Optimization (PPO) to approximate optimal policies for team decision-making.
Empirical results demonstrate that the RL agent successfully learns strategic bidding behavior that aligns with dynamic programming benchmarks in simplified settings while scaling effectively to larger, intractable environments. The study further extends reinforcement learning applications to a job scheduling problem, where an agent must allocate resources to maximize returns under uncertainty, and to a capacity-constrained Cournot market, where firms strategically invest to maximize long-term profitability.
Findings indicate that reinforcement learning serves as a powerful tool for approximating optimal strategies in complex, non-tractable markets. This work contributes to the growing intersection of computational economics, market design, and artificial intelligence by showcasing the effectiveness of reinforcement learning in decision-support systems for economic and strategic environments.
"]},{"key":"dc:source","label":"Dc Source","values":["J. Cohn, \"Reinforcement learning, modeling markets, and professional basketball free agency,\" Ph.D. dissertation, Chapman University, Orange, CA, 2025. https://doi.org/10.36837/chapman.000687"]},{"key":"dc:title","label":"Title","values":["Reinforcement Learning, Modeling Markets, and Professional Basketball Free Agency"]}]}],"canonical_facts":{"dc:contributor":["David Porter","Stephen Rassenti","Ryan French"],"dc:creator":["Cohn, Jacob"],"dc:date.available":["2026-05-09T07:00:00Z"],"dc:description.abstract":["This dissertation presents a reinforcement learning-based approach to modeling and optimizing decision-making in professional basketball free agency and related economic environments. A Markov Decision Process (MDP) framework is introduced to capture the strategic interactions of NBA teams bidding for free agents under budgetary and roster constraints. To address computational scalability challenges, a reinforcement learning (RL) environment is developed, leveraging Proximal Policy Optimization (PPO) to approximate optimal policies for team decision-making.
Empirical results demonstrate that the RL agent successfully learns strategic bidding behavior that aligns with dynamic programming benchmarks in simplified settings while scaling effectively to larger, intractable environments. The study further extends reinforcement learning applications to a job scheduling problem, where an agent must allocate resources to maximize returns under uncertainty, and to a capacity-constrained Cournot market, where firms strategically invest to maximize long-term profitability.
Findings indicate that reinforcement learning serves as a powerful tool for approximating optimal strategies in complex, non-tractable markets. This work contributes to the growing intersection of computational economics, market design, and artificial intelligence by showcasing the effectiveness of reinforcement learning in decision-support systems for economic and strategic environments.
"],"dc:identifier":["https://digitalcommons.chapman.edu/cads_dissertations/49"],"dc:source":["J. Cohn, \"Reinforcement learning, modeling markets, and professional basketball free agency,\" Ph.D. dissertation, Chapman University, Orange, CA, 2025. https://doi.org/10.36837/chapman.000687"],"dc:subject":["Free Agency","Reinforcement Learning","Scheduling","Cournot","Dynamic Programming","Markets","Artificial Intelligence and Robotics","Behavioral Economics","Data Science","Design of Experiments and Sample Surveys","Labor Economics"],"dc:title":["Reinforcement Learning, Modeling Markets, and Professional Basketball Free Agency"],"thesis:degree_discipline":["Computational and Data Sciences"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Doctor of Philosophy (PhD)"]},"updated_at":"2026-07-24T01:38:43Z"}