{"id":{"repo_id":"clemson","oai_identifier":"oai:open.clemson.edu:all_theses-4525"},"canonical_url":"https://search.ndltd.org/etd/clemson/oai:open.clemson.edu:all_theses-4525","repository":{"repo_id":"clemson","name":"Clemson University","base_url":"https://open.clemson.edu/do/oai/"},"display":{"title":"Training Physics-based Controllers for Articulated Characters with Deep Reinforcement Learning","abstract":"In this thesis, two different applications are discussed for using machine learning techniques to train coordinated motion controllers in arbitrary characters in absence of motion capture data. The methods highlight the resourcefulness of physical simulations to generate synthetic and generic motion data that can be used to learn various targeted skills. First, we present an unsupervised method for learning loco-motion skills in virtual characters from a low dimensional latent space which captures the coordination between multiple joints. We use a technique called motor babble, wherein a character interacts with its environment by actuating its joints through uncoordinated, low-level (motor) excitation, resulting in a corpus of motion data from which a manifold latent space can be extracted. Using reinforcement learning, we then train the character to learn locomotion (such as walking or running) in the low-dimensional latent space instead of the full-dimensional joint action space. The thesis also presents an end-to-end automated framework for training physics-based characters to rhythmically dance to user-input songs. A generative adversarial network (GAN) architecture is proposed that learns to generate physically stable dance moves through repeated interactions with the environment. These moves are then used to construct a dance network that can be used for choreography. Using DRL, the character is then trained to perform these moves, without losing balance and rhythm, in the presence of physical forces such as gravity and friction.","abstract_html":"In this thesis, two different applications are discussed for using machine learning techniques to train coordinated motion controllers in arbitrary characters in absence of motion capture data. The methods highlight the resourcefulness of physical simulations to generate synthetic and generic motion data that can be used to learn various targeted skills. First, we present an unsupervised method for learning loco-motion skills in virtual characters from a low dimensional latent space which captures the coordination between multiple joints. We use a technique called motor babble, wherein a character interacts with its environment by actuating its joints through uncoordinated, low-level (motor) excitation, resulting in a corpus of motion data from which a manifold latent space can be extracted. Using reinforcement learning, we then train the character to learn locomotion (such as walking or running) in the low-dimensional latent space instead of the full-dimensional joint action space. The thesis also presents an end-to-end automated framework for training physics-based characters to rhythmically dance to user-input songs. A generative adversarial network (GAN) architecture is proposed that learns to generate physically stable dance moves through repeated interactions with the environment. These moves are then used to construct a dance network that can be used for choreography. Using DRL, the character is then trained to perform these moves, without losing balance and rhythm, in the presence of physical forces such as gravity and friction.","abstract_has_math":false,"creators":["Biswas, Avishek"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"School of Computing","degree_department":null,"school":null,"contributors":["Ioannis Karamouzas","Daljit S Dhillon"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:28:20Z","subjects":["Character Animation","Reinforcement Learning"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://open.clemson.edu/all_theses/3518","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://open.clemson.edu/all_theses/3518","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://open.clemson.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Aopen.clemson.edu%3Aall_theses-4525","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Ioannis Karamouzas","Daljit S Dhillon"]},{"key":"dc:creator","label":"Author","values":["Biswas, Avishek"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.created","label":"Dc Date Created","values":["2021-05-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["School of Computing"]},{"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":["Character Animation","Reinforcement Learning"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://open.clemson.edu/all_theses/3518"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["In this thesis, two different applications are discussed for using machine learning techniques to train coordinated motion controllers in arbitrary characters in absence of motion capture data. The methods highlight the resourcefulness of physical simulations to generate synthetic and generic motion data that can be used to learn various targeted skills. First, we present an unsupervised method for learning loco-motion skills in virtual characters from a low dimensional latent space which captures the coordination between multiple joints. We use a technique called motor babble, wherein a character interacts with its environment by actuating its joints through uncoordinated, low-level (motor) excitation, resulting in a corpus of motion data from which a manifold latent space can be extracted. Using reinforcement learning, we then train the character to learn locomotion (such as walking or running) in the low-dimensional latent space instead of the full-dimensional joint action space. The thesis also presents an end-to-end automated framework for training physics-based characters to rhythmically dance to user-input songs. A generative adversarial network (GAN) architecture is proposed that learns to generate physically stable dance moves through repeated interactions with the environment. These moves are then used to construct a dance network that can be used for choreography. Using DRL, the character is then trained to perform these moves, without losing balance and rhythm, in the presence of physical forces such as gravity and friction."]},{"key":"dc:title","label":"Title","values":["Training Physics-based Controllers for Articulated Characters with Deep Reinforcement Learning"]}]}],"canonical_facts":{"dc:contributor":["Ioannis Karamouzas","Daljit S Dhillon"],"dc:creator":["Biswas, Avishek"],"dc:date.created":["2021-05-01T07:00:00Z"],"dc:description.abstract":["In this thesis, two different applications are discussed for using machine learning techniques to train coordinated motion controllers in arbitrary characters in absence of motion capture data. The methods highlight the resourcefulness of physical simulations to generate synthetic and generic motion data that can be used to learn various targeted skills. First, we present an unsupervised method for learning loco-motion skills in virtual characters from a low dimensional latent space which captures the coordination between multiple joints. We use a technique called motor babble, wherein a character interacts with its environment by actuating its joints through uncoordinated, low-level (motor) excitation, resulting in a corpus of motion data from which a manifold latent space can be extracted. Using reinforcement learning, we then train the character to learn locomotion (such as walking or running) in the low-dimensional latent space instead of the full-dimensional joint action space. The thesis also presents an end-to-end automated framework for training physics-based characters to rhythmically dance to user-input songs. A generative adversarial network (GAN) architecture is proposed that learns to generate physically stable dance moves through repeated interactions with the environment. These moves are then used to construct a dance network that can be used for choreography. Using DRL, the character is then trained to perform these moves, without losing balance and rhythm, in the presence of physical forces such as gravity and friction."],"dc:identifier":["https://open.clemson.edu/all_theses/3518"],"dc:subject":["Character Animation","Reinforcement Learning"],"dc:title":["Training Physics-based Controllers for Articulated Characters with Deep Reinforcement Learning"],"thesis:degree_discipline":["School of Computing"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T07:28:20Z"}