{"id":{"repo_id":"calpoly","oai_identifier":"oai:digitalcommons.calpoly.edu:theses-3517"},"canonical_url":"https://search.ndltd.org/etd/calpoly/oai:digitalcommons.calpoly.edu:theses-3517","repository":{"repo_id":"calpoly","name":"Cal Poly","base_url":"https://digitalcommons.calpoly.edu/do/oai/"},"display":{"title":"Utilizing Trajectory Optimization in the Training of Neural Network Controllers","abstract":"Applying reinforcement learning to control systems enables the use of machine learning to develop elegant and efficient control laws. Coupled with the representational power of neural networks, reinforcement learning algorithms can learn complex policies that can be difficult to emulate using traditional control system design approaches. In this thesis, three different model-free reinforcement learning algorithms, including Monte Carlo Control, REINFORCE with baseline, and Guided Policy Search are compared in simulated, continuous action-space environments. The results show that the Guided Policy Search algorithm is able to learn a desired control policy much faster than the other algorithms. In the inverted pendulum system, it learns an effective policy up to three times faster than the other algorithms. In the cartpole system, it learns an effective policy up to nearly fifteen times faster than the other algorithms.","abstract_html":"Applying reinforcement learning to control systems enables the use of machine learning to develop elegant and efficient control laws. Coupled with the representational power of neural networks, reinforcement learning algorithms can learn complex policies that can be difficult to emulate using traditional control system design approaches. In this thesis, three different model-free reinforcement learning algorithms, including Monte Carlo Control, REINFORCE with baseline, and Guided Policy Search are compared in simulated, continuous action-space environments. The results show that the Guided Policy Search algorithm is able to learn a desired control policy much faster than the other algorithms. In the inverted pendulum system, it learns an effective policy up to three times faster than the other algorithms. In the cartpole system, it learns an effective policy up to nearly fifteen times faster than the other algorithms.","abstract_has_math":false,"creators":["Kimball, Nicholas"],"institution":null,"degree_name":"MS in Electrical Engineering","degree_level":null,"degree_discipline":"Electrical Engineering","degree_department":null,"school":null,"contributors":["Helen Yu"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:11:57Z","subjects":["Reinforcement Learning","Optimal Control","Trajectory Optimization","iLQR","Guided Policy Search","Neural Networks","Controls and Control Theory","Other Electrical and Computer Engineering","Robotics"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["10.15368/theses.2019.87"],"render_values":[{"text":"10.15368/theses.2019.87","href":"https://doi.org/10.15368/theses.2019.87","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/2071","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.calpoly.edu/theses/2071","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.calpoly.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.calpoly.edu%3Atheses-3517","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Helen Yu"]},{"key":"dc:creator","label":"Author","values":["Kimball, Nicholas"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2022-09-04T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2019-09-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical Engineering"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Electrical Engineering"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Reinforcement Learning","Optimal Control","Trajectory Optimization","iLQR","Guided Policy Search","Neural Networks","Controls and Control Theory","Other Electrical and Computer Engineering","Robotics"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/2071","10.15368/theses.2019.87"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Applying reinforcement learning to control systems enables the use of machine learning to develop elegant and efficient control laws. Coupled with the representational power of neural networks, reinforcement learning algorithms can learn complex policies that can be difficult to emulate using traditional control system design approaches. In this thesis, three different model-free reinforcement learning algorithms, including Monte Carlo Control, REINFORCE with baseline, and Guided Policy Search are compared in simulated, continuous action-space environments. The results show that the Guided Policy Search algorithm is able to learn a desired control policy much faster than the other algorithms. In the inverted pendulum system, it learns an effective policy up to three times faster than the other algorithms. In the cartpole system, it learns an effective policy up to nearly fifteen times faster than the other algorithms."]},{"key":"dc:title","label":"Title","values":["Utilizing Trajectory Optimization in the Training of Neural Network Controllers"]}]}],"canonical_facts":{"dc:contributor":["Helen Yu"],"dc:creator":["Kimball, Nicholas"],"dc:date.available":["2022-09-04T07:00:00Z"],"dc:date.created":["2019-09-01T07:00:00Z"],"dc:description.abstract":["Applying reinforcement learning to control systems enables the use of machine learning to develop elegant and efficient control laws. Coupled with the representational power of neural networks, reinforcement learning algorithms can learn complex policies that can be difficult to emulate using traditional control system design approaches. In this thesis, three different model-free reinforcement learning algorithms, including Monte Carlo Control, REINFORCE with baseline, and Guided Policy Search are compared in simulated, continuous action-space environments. The results show that the Guided Policy Search algorithm is able to learn a desired control policy much faster than the other algorithms. In the inverted pendulum system, it learns an effective policy up to three times faster than the other algorithms. In the cartpole system, it learns an effective policy up to nearly fifteen times faster than the other algorithms."],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/2071","10.15368/theses.2019.87"],"dc:subject":["Reinforcement Learning","Optimal Control","Trajectory Optimization","iLQR","Guided Policy Search","Neural Networks","Controls and Control Theory","Other Electrical and Computer Engineering","Robotics"],"dc:title":["Utilizing Trajectory Optimization in the Training of Neural Network Controllers"],"thesis:degree_discipline":["Electrical Engineering"],"thesis:degree_name":["MS in Electrical Engineering"]},"updated_at":"2026-11-19T07:11:57Z"}