{"id":{"repo_id":"toronto-retro","oai_identifier":"oai:utoronto.scholaris.ca:1807/68193"},"canonical_url":"https://search.dev.ndltd.org/etd/toronto-retro/oai:utoronto.scholaris.ca:1807/68193","repository":{"repo_id":"toronto-retro","name":"University of Toronto","base_url":"https://utoronto.scholaris.ca/server/oai/request"},"display":{"title":"Evolvable Mathematical Models: A New Artificial Intelligence Paradigm","abstract":"We develop a novel Artificial Intelligence paradigm to generate autonomously artificial agents as mathematical models of behaviour. Agent/environment inputs are mapped to agent outputs via equation trees which are evolved in a manner similar to Symbolic Regression in Genetic Programming. Equations are comprised of only the four basic mathematical operators, addition, subtraction, multiplication and division, as well as input and output variables and constants. From these operations, equations can be constructed that approximate any analytic function. These Evolvable Mathematical Models (EMMs) are tested and compared to their Artificial Neural Network (ANN) counterparts on two benchmarking tasks: the double-pole balancing without velocity information benchmark and the challenging discrete Double-T Maze experiments with homing. The results from these experiments show that EMMs are capable of solving tasks typically solved by ANNs, and that they have the ability to produce agents that demonstrate learning behaviours. To further explore the capabilities of EMMs, as well as to investigate the evolutionary origins of communication, we develop","abstract_html":"We develop a novel Artificial Intelligence paradigm to generate autonomously artificial agents as mathematical models of behaviour. Agent/environment inputs are mapped to agent outputs via equation trees which are evolved in a manner similar to Symbolic Regression in Genetic Programming. Equations are comprised of only the four basic mathematical operators, addition, subtraction, multiplication and division, as well as input and output variables and constants. From these operations, equations can be constructed that approximate any analytic function. These Evolvable Mathematical Models (EMMs) are tested and compared to their Artificial Neural Network (ANN) counterparts on two benchmarking tasks: the double-pole balancing without velocity information benchmark and the challenging discrete Double-T Maze experiments with homing. The results from these experiments show that EMMs are capable of solving tasks typically solved by ANNs, and that they have the ability to produce agents that demonstrate learning behaviours. To further explore the capabilities of EMMs, as well as to investigate the evolutionary origins of communication, we develop","abstract_has_math":false,"creators":["Grouchy, Paul"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Aerospace Science and Engineering","school":null,"contributors":[],"advisors":["Gabriele, M.T. D'Eleuterio"],"committee_chairs":[],"committee_members":[],"year":2014,"date_issued":"2014-11","date_published":"2014-11","updated_at":"2026-07-27T21:28:05Z","subjects":["Artificial Intelligence","Artificial Life","Evolutionary Computation","Evolutionary Robotics","Genetic Programming"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1807/68193","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Gabriele, M.T. D'Eleuterio"]},{"key":"dc:contributor.department","label":"Department","values":["Aerospace Science and Engineering"]},{"key":"dc:creator","label":"Author","values":["Grouchy, Paul"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2014-11"]},{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2015-04-22T20:13:55Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2015-04-22T20:13:55Z"]},{"key":"dc:date.issued","label":"Date","values":["2014-11"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Artificial Intelligence","Artificial Life","Evolutionary Computation","Evolutionary Robotics","Genetic Programming"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1807/68193"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["We develop a novel Artificial Intelligence paradigm to generate autonomously artificial agents as mathematical models of behaviour. Agent/environment inputs are mapped to agent outputs via equation trees which are evolved in a manner similar to Symbolic Regression in Genetic Programming. Equations are comprised of only the four basic mathematical operators, addition, subtraction, multiplication and division, as well as input and output variables and constants. From these operations, equations can be constructed that approximate any analytic function. These Evolvable Mathematical Models (EMMs) are tested and compared to their Artificial Neural Network (ANN) counterparts on two benchmarking tasks: the double-pole balancing without velocity information benchmark and the challenging discrete Double-T Maze experiments with homing. The results from these experiments show that EMMs are capable of solving tasks typically solved by ANNs, and that they have the ability to produce agents that demonstrate learning behaviours. To further explore the capabilities of EMMs, as well as to investigate the evolutionary origins of communication, we develop"]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ph.D."]},{"key":"dc:title","label":"Title","values":["Evolvable Mathematical Models: A New Artificial Intelligence Paradigm"]}]}],"canonical_facts":{"dc:contributor.advisor":["Gabriele, M.T. D'Eleuterio"],"dc:contributor.department":["Aerospace Science and Engineering"],"dc:creator":["Grouchy, Paul"],"dc:date":["2014-11"],"dc:date.accessioned":["2015-04-22T20:13:55Z"],"dc:date.available":["2015-04-22T20:13:55Z"],"dc:date.issued":["2014-11"],"dc:description.abstract":["We develop a novel Artificial Intelligence paradigm to generate autonomously artificial agents as mathematical models of behaviour. Agent/environment inputs are mapped to agent outputs via equation trees which are evolved in a manner similar to Symbolic Regression in Genetic Programming. Equations are comprised of only the four basic mathematical operators, addition, subtraction, multiplication and division, as well as input and output variables and constants. From these operations, equations can be constructed that approximate any analytic function. These Evolvable Mathematical Models (EMMs) are tested and compared to their Artificial Neural Network (ANN) counterparts on two benchmarking tasks: the double-pole balancing without velocity information benchmark and the challenging discrete Double-T Maze experiments with homing. The results from these experiments show that EMMs are capable of solving tasks typically solved by ANNs, and that they have the ability to produce agents that demonstrate learning behaviours. To further explore the capabilities of EMMs, as well as to investigate the evolutionary origins of communication, we develop"],"dc:description.degree":["Ph.D."],"dc:identifier.uri":["http://hdl.handle.net/1807/68193"],"dc:subject":["Artificial Intelligence","Artificial Life","Evolutionary Computation","Evolutionary Robotics","Genetic Programming"],"dc:title":["Evolvable Mathematical Models: A New Artificial Intelligence Paradigm"],"dc:type":["Thesis"]},"updated_at":"2026-07-27T21:28:05Z"}