{"id":{"repo_id":"utahstate","oai_identifier":"oai:digitalcommons.usu.edu:etd-9296"},"canonical_url":"https://search.ndltd.org/etd/utahstate/oai:digitalcommons.usu.edu:etd-9296","repository":{"repo_id":"utahstate","name":"Utah State University","base_url":"https://digitalcommons.usu.edu/do/oai/"},"display":{"title":"Intraday Stock Trading Using Reinforcement Learning: An Investigation of Visual Representations of Price","abstract":"In this study, we are developing a reinforcement learning-based strategy for the intraday trading of stocks. This study’s primary goals include developing an environment that can be used as a simulator for the day trading stock market and, train an agent to trade in this environment by performing actions and finding the optimal policy to maximize its reward. This study also focuses on experimentation with different state representations to understand how data representation affects the learning system. We have experimented with three different state representations. All the representations focus on presenting the intraday stock data as images. We have chosen images rather than numerical data as our state representative to make it human interpretable. We want the agent to learn the insights from patterns and trends and apply that knowledge to make a profit, just like a seasoned human trader. We have also experimented with two different learning algorithms, the effects of exploration rate decay and the effects of reward penalty.","abstract_html":"In this study, we are developing a reinforcement learning-based strategy for the intraday trading of stocks. This study’s primary goals include developing an environment that can be used as a simulator for the day trading stock market and, train an agent to trade in this environment by performing actions and finding the optimal policy to maximize its reward. This study also focuses on experimentation with different state representations to understand how data representation affects the learning system. We have experimented with three different state representations. All the representations focus on presenting the intraday stock data as images. We have chosen images rather than numerical data as our state representative to make it human interpretable. We want the agent to learn the insights from patterns and trends and apply that knowledge to make a profit, just like a seasoned human trader. We have also experimented with two different learning algorithms, the effects of exploration rate decay and the effects of reward penalty.","abstract_has_math":false,"creators":["Tenguria, Kanak"],"institution":"Hosted by Utah State University Libraries","degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Nicholas S. Flann","Vladimir Kulyukin","Chad Mano"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:52:35Z","subjects":["stock","deep learning","support and resistance","visual representation of stock price","candlestick chart","gradient","score","reinforcement learning","convolution neural networks","environment","agent","reward","buy","sell","hold","chart patterns","intra-day stock trading","day trading","price representation","Deep-Q Networks","Double deep-q networks","reward penalty","cumulative reward","Computer Sciences"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.26076/bf94-59d1"],"render_values":[{"text":"https://doi.org/10.26076/bf94-59d1","href":"https://doi.org/10.26076/bf94-59d1","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usu.edu/etd/8154","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usu.edu/etd/8154","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.usu.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.usu.edu%3Aetd-9296","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Nicholas S. Flann","Vladimir Kulyukin","Chad Mano"]},{"key":"dc:creator","label":"Author","values":["Tenguria, Kanak"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2026-08-01T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2021-08-01T07:00:00Z"]},{"key":"dc:publisher","label":"Institution","values":["Hosted by Utah State University Libraries"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["stock","deep learning","support and resistance","visual representation of stock price","candlestick chart","gradient","score","reinforcement learning","convolution neural networks","environment","agent","reward","buy","sell","hold","chart patterns","intra-day stock trading","day trading","price representation","Deep-Q Networks","Double deep-q networks","reward penalty","cumulative reward","Computer Sciences"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usu.edu/etd/8154"]},{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.26076/bf94-59d1"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["In this study, we are developing a reinforcement learning-based strategy for the intraday trading of stocks. This study’s primary goals include developing an environment that can be used as a simulator for the day trading stock market and, train an agent to trade in this environment by performing actions and finding the optimal policy to maximize its reward. This study also focuses on experimentation with different state representations to understand how data representation affects the learning system. We have experimented with three different state representations. All the representations focus on presenting the intraday stock data as images. We have chosen images rather than numerical data as our state representative to make it human interpretable. We want the agent to learn the insights from patterns and trends and apply that knowledge to make a profit, just like a seasoned human trader. We have also experimented with two different learning algorithms, the effects of exploration rate decay and the effects of reward penalty."]},{"key":"dc:title","label":"Title","values":["Intraday Stock Trading Using Reinforcement Learning: An Investigation of Visual Representations of Price"]}]}],"canonical_facts":{"dc:contributor":["Nicholas S. Flann","Vladimir Kulyukin","Chad Mano"],"dc:creator":["Tenguria, Kanak"],"dc:date.available":["2026-08-01T07:00:00Z"],"dc:date.created":["2021-08-01T07:00:00Z"],"dc:description.abstract":["In this study, we are developing a reinforcement learning-based strategy for the intraday trading of stocks. This study’s primary goals include developing an environment that can be used as a simulator for the day trading stock market and, train an agent to trade in this environment by performing actions and finding the optimal policy to maximize its reward. This study also focuses on experimentation with different state representations to understand how data representation affects the learning system. We have experimented with three different state representations. All the representations focus on presenting the intraday stock data as images. We have chosen images rather than numerical data as our state representative to make it human interpretable. We want the agent to learn the insights from patterns and trends and apply that knowledge to make a profit, just like a seasoned human trader. We have also experimented with two different learning algorithms, the effects of exploration rate decay and the effects of reward penalty."],"dc:identifier":["https://digitalcommons.usu.edu/etd/8154"],"dc:identifier.doi":["https://doi.org/10.26076/bf94-59d1"],"dc:publisher":["Hosted by Utah State University Libraries"],"dc:subject":["stock","deep learning","support and resistance","visual representation of stock price","candlestick chart","gradient","score","reinforcement learning","convolution neural networks","environment","agent","reward","buy","sell","hold","chart patterns","intra-day stock trading","day trading","price representation","Deep-Q Networks","Double deep-q networks","reward penalty","cumulative reward","Computer Sciences"],"dc:title":["Intraday Stock Trading Using Reinforcement Learning: An Investigation of Visual Representations of Price"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T08:52:35Z"}