{"id":{"repo_id":"helsinki","oai_identifier":"oai:helda.helsinki.fi:10138/577825"},"canonical_url":"https://search.dev.ndltd.org/etd/helsinki/oai:helda.helsinki.fi:10138/577825","repository":{"repo_id":"helsinki","name":"University of Helsinki","base_url":"https://helda.helsinki.fi/server/oai/request"},"display":{"title":"Learning How Humans Play Board Games with GPT-4IAR","abstract":"Planning and decision making are active areas of research in cognitive neuroscience that strive to explain how the brain makes decisions in complex scenarios. Research in this field has traditionally been restricted to simplistic experiments such as two-alternative forced choice situations, and has relatively recently broken into more naturalistic settings with the help of computational modeling and games. Importantly, these computational models aim to be interpretable, meaning that they are crafted in a way that what each parameter means has a clear meaning, perhaps in contrast to massive neural networks. However, the latter may better capture more complex behaviors that the hand-crafted model could miss, so it may be desirable to use a neural network as a guide or ``oracle'' to study and improve the parameters to include in the interpretable model. In this thesis, we present GPT-4IAR, a transformer neural network architecture for modeling and predicting human behavior in the board game four-in-a-row (4IAR). Building upon previous studies that use fully connected neural networks to improve models around 4IAR, and the excellent capabilities of the GPT architecture in tasks where data is sequential, we train a transformer on millions of games of 4IAR to study biases that arise in human decision making. Experiments show that conditioning action predictions on longer histories of previous moves leads to improved accuracy over prior state-of-the-art models, hinting at longer-term strategic biases in human gameplay. Reaction time prediction is also explored, showing promise in capturing meaningful gameplay statistics beyond raw actions.","abstract_html":"Planning and decision making are active areas of research in cognitive neuroscience that strive to explain how the brain makes decisions in complex scenarios. Research in this field has traditionally been restricted to simplistic experiments such as two-alternative forced choice situations, and has relatively recently broken into more naturalistic settings with the help of computational modeling and games. Importantly, these computational models aim to be interpretable, meaning that they are crafted in a way that what each parameter means has a clear meaning, perhaps in contrast to massive neural networks. However, the latter may better capture more complex behaviors that the hand-crafted model could miss, so it may be desirable to use a neural network as a guide or ``oracle'' to study and improve the parameters to include in the interpretable model. In this thesis, we present GPT-4IAR, a transformer neural network architecture for modeling and predicting human behavior in the board game four-in-a-row (4IAR). Building upon previous studies that use fully connected neural networks to improve models around 4IAR, and the excellent capabilities of the GPT architecture in tasks where data is sequential, we train a transformer on millions of games of 4IAR to study biases that arise in human decision making. Experiments show that conditioning action predictions on longer histories of previous moves leads to improved accuracy over prior state-of-the-art models, hinting at longer-term strategic biases in human gameplay. Reaction time prediction is also explored, showing promise in capturing meaningful gameplay statistics beyond raw actions.","abstract_has_math":false,"creators":["Yeom Song, Victor Manuel"],"institution":"Helsingin yliopisto","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Helsingin yliopisto, Matemaattis-luonnontieteellinen tiedekunta","University of Helsinki, Faculty of Science","Helsingfors universitet, Matematisk-naturvetenskapliga fakulteten"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024","date_published":"2024","updated_at":"2026-07-27T19:56:01Z","subjects":["Generative Pre-Trained Transformers","Human Decision Making","Neural Networks"],"languages":["eng"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["URN:NBN:fi:hulib-202406253314"],"render_values":[{"text":"URN:NBN:fi:hulib-202406253314","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/10138/577825","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Helsingin yliopisto, Matemaattis-luonnontieteellinen tiedekunta","University of Helsinki, Faculty of Science","Helsingfors universitet, Matematisk-naturvetenskapliga fakulteten"]},{"key":"dc:creator","label":"Author","values":["Yeom Song, Victor Manuel"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.issued","label":"Date","values":["2024"]},{"key":"dc:publisher","label":"Institution","values":["Helsingin yliopisto","University of Helsinki","Helsingfors universitet"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Generative Pre-Trained Transformers","Human Decision Making","Neural Networks"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["URN:NBN:fi:hulib-202406253314","http://hdl.handle.net/10138/577825"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Planning and decision making are active areas of research in cognitive neuroscience that strive to explain how the brain makes decisions in complex scenarios. Research in this field has traditionally been restricted to simplistic experiments such as two-alternative forced choice situations, and has relatively recently broken into more naturalistic settings with the help of computational modeling and games. Importantly, these computational models aim to be interpretable, meaning that they are crafted in a way that what each parameter means has a clear meaning, perhaps in contrast to massive neural networks. However, the latter may better capture more complex behaviors that the hand-crafted model could miss, so it may be desirable to use a neural network as a guide or ``oracle'' to study and improve the parameters to include in the interpretable model. In this thesis, we present GPT-4IAR, a transformer neural network architecture for modeling and predicting human behavior in the board game four-in-a-row (4IAR). Building upon previous studies that use fully connected neural networks to improve models around 4IAR, and the excellent capabilities of the GPT architecture in tasks where data is sequential, we train a transformer on millions of games of 4IAR to study biases that arise in human decision making. Experiments show that conditioning action predictions on longer histories of previous moves leads to improved accuracy over prior state-of-the-art models, hinting at longer-term strategic biases in human gameplay. Reaction time prediction is also explored, showing promise in capturing meaningful gameplay statistics beyond raw actions."]},{"key":"dc:title","label":"Title","values":["Learning How Humans Play Board Games with GPT-4IAR"]}]}],"canonical_facts":{"dc:contributor":["Helsingin yliopisto, Matemaattis-luonnontieteellinen tiedekunta","University of Helsinki, Faculty of Science","Helsingfors universitet, Matematisk-naturvetenskapliga fakulteten"],"dc:creator":["Yeom Song, Victor Manuel"],"dc:date.issued":["2024"],"dc:description.abstract":["Planning and decision making are active areas of research in cognitive neuroscience that strive to explain how the brain makes decisions in complex scenarios. Research in this field has traditionally been restricted to simplistic experiments such as two-alternative forced choice situations, and has relatively recently broken into more naturalistic settings with the help of computational modeling and games. Importantly, these computational models aim to be interpretable, meaning that they are crafted in a way that what each parameter means has a clear meaning, perhaps in contrast to massive neural networks. However, the latter may better capture more complex behaviors that the hand-crafted model could miss, so it may be desirable to use a neural network as a guide or ``oracle'' to study and improve the parameters to include in the interpretable model. In this thesis, we present GPT-4IAR, a transformer neural network architecture for modeling and predicting human behavior in the board game four-in-a-row (4IAR). Building upon previous studies that use fully connected neural networks to improve models around 4IAR, and the excellent capabilities of the GPT architecture in tasks where data is sequential, we train a transformer on millions of games of 4IAR to study biases that arise in human decision making. Experiments show that conditioning action predictions on longer histories of previous moves leads to improved accuracy over prior state-of-the-art models, hinting at longer-term strategic biases in human gameplay. Reaction time prediction is also explored, showing promise in capturing meaningful gameplay statistics beyond raw actions."],"dc:identifier.uri":["URN:NBN:fi:hulib-202406253314","http://hdl.handle.net/10138/577825"],"dc:language.iso":["eng"],"dc:publisher":["Helsingin yliopisto","University of Helsinki","Helsingfors universitet"],"dc:subject":["Generative Pre-Trained Transformers","Human Decision Making","Neural Networks"],"dc:title":["Learning How Humans Play Board Games with GPT-4IAR"]},"updated_at":"2026-07-27T19:56:01Z"}