{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/119007"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/119007","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"Encoding the Sensor Allocation Problem for Reinforcement Learning","abstract":"Traditionally, space situational awareness (SSA) sensor networks have relied on dynamic programming theory to generate tasking plans which govern how sensors are allocated to observe resident space objects. Deep reinforcement learning (DRL) techniques, with their ability to be trained on simulated environments, which are readily available for the SSA sensor allocation problem, and demonstrated performance in other fields, have potential to exceed performance of deterministic methods. The research presented in this dissertation develops techniques for encoding an SSA environment model to apply DRL to the sensor allocation problem. This dissertation is the compilation of two separate but related studies. The first study compares two alternative invalid action handling techniques, penalization and masking. The second study examines the performance of policies that have forecast state knowledge incorporated in the observation space.","abstract_html":"Traditionally, space situational awareness (SSA) sensor networks have relied on dynamic programming theory to generate tasking plans which govern how sensors are allocated to observe resident space objects. Deep reinforcement learning (DRL) techniques, with their ability to be trained on simulated environments, which are readily available for the SSA sensor allocation problem, and demonstrated performance in other fields, have potential to exceed performance of deterministic methods. The research presented in this dissertation develops techniques for encoding an SSA environment model to apply DRL to the sensor allocation problem. This dissertation is the compilation of two separate but related studies. The first study compares two alternative invalid action handling techniques, penalization and masking. The second study examines the performance of policies that have forecast state knowledge incorporated in the observation space.","abstract_has_math":false,"creators":["Penn, Dylan R."],"institution":"Virginia Tech","degree_name":"Doctor of Philosophy","degree_level":"doctoral","degree_discipline":"Aerospace Engineering","degree_department":"Aerospace and Ocean Engineering","school":null,"contributors":[],"advisors":[],"committee_chairs":["Black, Jonathan T."],"committee_members":["Schroeder, Kevin Kent","Smith, Leonard Allen","Fowler, Michael Chrispatrick"],"year":2024,"date_issued":"2024-05-16","date_published":"2024-05-16","updated_at":"2026-07-22T22:19:48Z","subjects":["space traffic management","resource allocation","reinforcement learning"],"languages":["en"],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:40264"],"render_values":[{"text":"vt_gsexam:40264","href":null,"code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/10919/119007","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Black, Jonathan T."]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Schroeder, Kevin Kent","Smith, Leonard Allen","Fowler, Michael Chrispatrick"]},{"key":"dc:contributor.department","label":"Department","values":["Aerospace and Ocean Engineering"]},{"key":"dc:creator","label":"Author","values":["Penn, Dylan R."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-05-17T08:00:45Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-05-17T08:00:45Z"]},{"key":"dc:date.issued","label":"Date","values":["2024-05-16"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Dissertation"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Aerospace Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["doctoral"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["space traffic management","resource allocation","reinforcement learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:40264"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10919/119007"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Traditionally, space situational awareness (SSA) sensor networks have relied on dynamic programming theory to generate tasking plans which govern how sensors are allocated to observe resident space objects. Deep reinforcement learning (DRL) techniques, with their ability to be trained on simulated environments, which are readily available for the SSA sensor allocation problem, and demonstrated performance in other fields, have potential to exceed performance of deterministic methods. The research presented in this dissertation develops techniques for encoding an SSA environment model to apply DRL to the sensor allocation problem. This dissertation is the compilation of two separate but related studies. The first study compares two alternative invalid action handling techniques, penalization and masking. The second study examines the performance of policies that have forecast state knowledge incorporated in the observation space."]},{"key":"dc:description.abstractgeneral","label":"General Abstract","values":["Resident space objects (RSOs) are typically tracked by ground-based sensors (telescopes and radar). Determining how to allocate sensors to RSOs is a complex problem traditionally performed by dynamic programming techniques. Deep reinforcement learning (DRL), a subset of machine learning, has demonstrated performance in other fields, and has the potential to exceed performance of traditional techniques. The research presented in this dissertation develops techniques for encoding a space situational awareness environment model to apply DRL to the sensor allocation problem. This dissertation is the compilation of two separate but related studies. The first study compares two alternative invalid action handling techniques, penalization and masking. The second study examines the performance of policies that have forecast state knowledge incorporated in the observation space."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Doctor of Philosophy"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["ETD"]},{"key":"dc:title","label":"Title","values":["Encoding the Sensor Allocation Problem for Reinforcement Learning"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Black, Jonathan T."],"dc:contributor.committeemember":["Schroeder, Kevin Kent","Smith, Leonard Allen","Fowler, Michael Chrispatrick"],"dc:contributor.department":["Aerospace and Ocean Engineering"],"dc:creator":["Penn, Dylan R."],"dc:date.accessioned":["2024-05-17T08:00:45Z"],"dc:date.available":["2024-05-17T08:00:45Z"],"dc:date.issued":["2024-05-16"],"dc:description.abstract":["Traditionally, space situational awareness (SSA) sensor networks have relied on dynamic programming theory to generate tasking plans which govern how sensors are allocated to observe resident space objects. Deep reinforcement learning (DRL) techniques, with their ability to be trained on simulated environments, which are readily available for the SSA sensor allocation problem, and demonstrated performance in other fields, have potential to exceed performance of deterministic methods. The research presented in this dissertation develops techniques for encoding an SSA environment model to apply DRL to the sensor allocation problem. This dissertation is the compilation of two separate but related studies. The first study compares two alternative invalid action handling techniques, penalization and masking. The second study examines the performance of policies that have forecast state knowledge incorporated in the observation space."],"dc:description.abstractgeneral":["Resident space objects (RSOs) are typically tracked by ground-based sensors (telescopes and radar). Determining how to allocate sensors to RSOs is a complex problem traditionally performed by dynamic programming techniques. Deep reinforcement learning (DRL), a subset of machine learning, has demonstrated performance in other fields, and has the potential to exceed performance of traditional techniques. The research presented in this dissertation develops techniques for encoding a space situational awareness environment model to apply DRL to the sensor allocation problem. This dissertation is the compilation of two separate but related studies. The first study compares two alternative invalid action handling techniques, penalization and masking. The second study examines the performance of policies that have forecast state knowledge incorporated in the observation space."],"dc:description.degree":["Doctor of Philosophy"],"dc:format.medium":["ETD"],"dc:identifier.other":["vt_gsexam:40264"],"dc:identifier.uri":["https://hdl.handle.net/10919/119007"],"dc:language.iso":["en"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["space traffic management","resource allocation","reinforcement learning"],"dc:title":["Encoding the Sensor Allocation Problem for Reinforcement Learning"],"dc:type":["Dissertation"],"thesis:degree_discipline":["Aerospace Engineering"],"thesis:degree_level":["doctoral"],"thesis:degree_name":["Doctor of Philosophy"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-22T22:19:48Z"}