{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/139143"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/139143","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents","abstract":"Performance of state-of-the art offline and model-based reinforcement learning (RL) algorithms deteriorates significantly when subjected to severe data scarcity and the presence of heterogeneous agents. In this work, we propose a model-based offline RL method to approach this setting. Using all available data from the various agents, we construct personalized simulators for each individual agent, which are then used to train RL policies. We do so by modeling the transition dynamics of the agents as a low rank tensor decomposition of latent factors associated with agents, states, and actions. We perform experiments on various benchmark environments and demonstrate improvement over existing offline approaches in the scarce data regime.","abstract_html":"Performance of state-of-the art offline and model-based reinforcement learning (RL) algorithms deteriorates significantly when subjected to severe data scarcity and the presence of heterogeneous agents. In this work, we propose a model-based offline RL method to approach this setting. Using all available data from the various agents, we construct personalized simulators for each individual agent, which are then used to train RL policies. We do so by modeling the transition dynamics of the agents as a low rank tensor decomposition of latent factors associated with agents, states, and actions. We perform experiments on various benchmark environments and demonstrate improvement over existing offline approaches in the scarce data regime.","abstract_has_math":false,"creators":["Alumootil, Varkey"],"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":["Shah, Devavrat"],"committee_chairs":[],"committee_members":[],"year":2021,"date_issued":"2021-06","date_published":"2021-06","updated_at":"2026-07-22T22:21:01Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"rights_urls":["http://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/139143","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Shah, Devavrat"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Alumootil, Varkey"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2022-01-14T14:52:30Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2022-01-14T14:52:30Z"]},{"key":"dc:date.issued","label":"Date","values":["2021-06"]},{"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 Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright MIT"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/139143"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Performance of state-of-the art offline and model-based reinforcement learning (RL) algorithms deteriorates significantly when subjected to severe data scarcity and the presence of heterogeneous agents. In this work, we propose a model-based offline RL method to approach this setting. Using all available data from the various agents, we construct personalized simulators for each individual agent, which are then used to train RL policies. We do so by modeling the transition dynamics of the agents as a low rank tensor decomposition of latent factors associated with agents, states, and actions. We perform experiments on various benchmark environments and demonstrate improvement over existing offline approaches in the scarce data regime."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents"]}]}],"canonical_facts":{"dc:contributor.advisor":["Shah, Devavrat"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Alumootil, Varkey"],"dc:date.accessioned":["2022-01-14T14:52:30Z"],"dc:date.available":["2022-01-14T14:52:30Z"],"dc:date.issued":["2021-06"],"dc:description.abstract":["Performance of state-of-the art offline and model-based reinforcement learning (RL) algorithms deteriorates significantly when subjected to severe data scarcity and the presence of heterogeneous agents. In this work, we propose a model-based offline RL method to approach this setting. Using all available data from the various agents, we construct personalized simulators for each individual agent, which are then used to train RL policies. We do so by modeling the transition dynamics of the agents as a low rank tensor decomposition of latent factors associated with agents, states, and actions. We perform experiments on various benchmark environments and demonstrate improvement over existing offline approaches in the scarce data regime."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/139143"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"dc:rights.uri":["http://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:21:01Z"}