{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/153888"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/153888","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Winning at Pokémon Random Battles Using Reinforcement Learning","abstract":"Pokémon battling is a challenging domain for reinforcement learning techniques, due to the massive state space, stochasticity, and partial observability. We demonstrate an agent which employs a Monte Carlo Tree Search informed by a actor-critic network trained using Proximal Policy Optimization with experience collected through self-play. The agent peaked at rank 8 (1693 Elo) on the official Pokémon Showdown gen4randombattles ladder, which is the best known performance by any non-human agent for this format. This strong showing lays the foundation for superhuman performance in Pokémon and other complex turn-based games of imperfect information, expanding the viability of methods which have historically been used in perfect-information games.","abstract_html":"Pokémon battling is a challenging domain for reinforcement learning techniques, due to the massive state space, stochasticity, and partial observability. We demonstrate an agent which employs a Monte Carlo Tree Search informed by a actor-critic network trained using Proximal Policy Optimization with experience collected through self-play. The agent peaked at rank 8 (1693 Elo) on the official Pokémon Showdown gen4randombattles ladder, which is the best known performance by any non-human agent for this format. This strong showing lays the foundation for superhuman performance in Pokémon and other complex turn-based games of imperfect information, expanding the viability of methods which have historically been used in perfect-information games.","abstract_has_math":false,"creators":["Wang, Jett"],"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":["Tenenbaum, Joshua"],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-02","date_published":"2024-02","updated_at":"2026-07-22T22:21:43Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"rights_urls":["https://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/153888","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Tenenbaum, Joshua"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Wang, Jett"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-03-21T19:13:48Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-03-21T19:13:48Z"]},{"key":"dc:date.issued","label":"Date","values":["2024-02"]},{"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 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 retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/153888"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Pokémon battling is a challenging domain for reinforcement learning techniques, due to the massive state space, stochasticity, and partial observability. We demonstrate an agent which employs a Monte Carlo Tree Search informed by a actor-critic network trained using Proximal Policy Optimization with experience collected through self-play. The agent peaked at rank 8 (1693 Elo) on the official Pokémon Showdown gen4randombattles ladder, which is the best known performance by any non-human agent for this format. This strong showing lays the foundation for superhuman performance in Pokémon and other complex turn-based games of imperfect information, expanding the viability of methods which have historically been used in perfect-information games."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Winning at Pokémon Random Battles Using Reinforcement Learning"]}]}],"canonical_facts":{"dc:contributor.advisor":["Tenenbaum, Joshua"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Wang, Jett"],"dc:date.accessioned":["2024-03-21T19:13:48Z"],"dc:date.available":["2024-03-21T19:13:48Z"],"dc:date.issued":["2024-02"],"dc:description.abstract":["Pokémon battling is a challenging domain for reinforcement learning techniques, due to the massive state space, stochasticity, and partial observability. We demonstrate an agent which employs a Monte Carlo Tree Search informed by a actor-critic network trained using Proximal Policy Optimization with experience collected through self-play. The agent peaked at rank 8 (1693 Elo) on the official Pokémon Showdown gen4randombattles ladder, which is the best known performance by any non-human agent for this format. This strong showing lays the foundation for superhuman performance in Pokémon and other complex turn-based games of imperfect information, expanding the viability of methods which have historically been used in perfect-information games."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/153888"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"dc:rights.uri":["https://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Winning at Pokémon Random Battles Using Reinforcement Learning"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:21:43Z"}