{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/163541"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/163541","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Problem-Independent Regrets on Expectation-Dependent Multi-Armed Bandits","abstract":"The independence axiom (IA) proposed by Von Neumann and Morgenstern [50] is the cornerstone of the expected utility theory. However, some empirical experiments show that the IA is often violated in the real world. We propose a new kind of multi-armed bandit problem where the expectation of outcomes may influence the agent’s utility which we call expectation-dependent multi-armed bandits and rationalize the choice of agents in Machina’s paradox lacking the IA. We design provably efficient algorithms with low minimax regrets and show their consistency of time horizon T with corresponding regret lower bounds, revealing statistical optimality. Furthermore, as we first consider bandits whose corresponding utility depends on both reality and expectation, it provides a bridge between machine learning and economic behavior theory, shedding light on how to interpret some counterintuitive economic scenarios, like bounded rationality explored by Zhang et al. [54].","abstract_html":"The independence axiom (IA) proposed by Von Neumann and Morgenstern [50] is the cornerstone of the expected utility theory. However, some empirical experiments show that the IA is often violated in the real world. We propose a new kind of multi-armed bandit problem where the expectation of outcomes may influence the agent’s utility which we call expectation-dependent multi-armed bandits and rationalize the choice of agents in Machina’s paradox lacking the IA. We design provably efficient algorithms with low minimax regrets and show their consistency of time horizon T with corresponding regret lower bounds, revealing statistical optimality. Furthermore, as we first consider bandits whose corresponding utility depends on both reality and expectation, it provides a bridge between machine learning and economic behavior theory, shedding light on how to interpret some counterintuitive economic scenarios, like bounded rationality explored by Zhang et al. [54].","abstract_has_math":false,"creators":["Ai, Rui"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Institute for Data, Systems, and Society","school":null,"contributors":[],"advisors":["Simchi-Levi, David"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-05","date_published":"2025-05","updated_at":"2026-07-22T22:22:16Z","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/1721.1/163541","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Simchi-Levi, David"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Institute for Data, Systems, and Society"]},{"key":"dc:creator","label":"Author","values":["Ai, Rui"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-11-05T19:33:20Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-11-05T19:33:20Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-05"]},{"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 Social and Engineering Systems"]}]},{"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/1721.1/163541"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The independence axiom (IA) proposed by Von Neumann and Morgenstern [50] is the cornerstone of the expected utility theory. However, some empirical experiments show that the IA is often violated in the real world. We propose a new kind of multi-armed bandit problem where the expectation of outcomes may influence the agent’s utility which we call expectation-dependent multi-armed bandits and rationalize the choice of agents in Machina’s paradox lacking the IA. We design provably efficient algorithms with low minimax regrets and show their consistency of time horizon T with corresponding regret lower bounds, revealing statistical optimality. Furthermore, as we first consider bandits whose corresponding utility depends on both reality and expectation, it provides a bridge between machine learning and economic behavior theory, shedding light on how to interpret some counterintuitive economic scenarios, like bounded rationality explored by Zhang et al. [54]."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:title","label":"Title","values":["Problem-Independent Regrets on Expectation-Dependent Multi-Armed Bandits"]}]}],"canonical_facts":{"dc:contributor.advisor":["Simchi-Levi, David"],"dc:contributor.department":["Massachusetts Institute of Technology. Institute for Data, Systems, and Society"],"dc:creator":["Ai, Rui"],"dc:date.accessioned":["2025-11-05T19:33:20Z"],"dc:date.available":["2025-11-05T19:33:20Z"],"dc:date.issued":["2025-05"],"dc:description.abstract":["The independence axiom (IA) proposed by Von Neumann and Morgenstern [50] is the cornerstone of the expected utility theory. However, some empirical experiments show that the IA is often violated in the real world. We propose a new kind of multi-armed bandit problem where the expectation of outcomes may influence the agent’s utility which we call expectation-dependent multi-armed bandits and rationalize the choice of agents in Machina’s paradox lacking the IA. We design provably efficient algorithms with low minimax regrets and show their consistency of time horizon T with corresponding regret lower bounds, revealing statistical optimality. Furthermore, as we first consider bandits whose corresponding utility depends on both reality and expectation, it provides a bridge between machine learning and economic behavior theory, shedding light on how to interpret some counterintuitive economic scenarios, like bounded rationality explored by Zhang et al. [54]."],"dc:description.degree":["S.M."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/163541"],"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":["Problem-Independent Regrets on Expectation-Dependent Multi-Armed Bandits"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Science in Social and Engineering Systems"]},"updated_at":"2026-07-22T22:22:16Z"}