dc.contributor.author | Wright, Matthew | |
dc.date.accessioned | 2020-08-20T14:12:41Z | |
dc.date.available | 2020-08-20T14:12:41Z | |
dc.date.issued | 2020-08-20T14:12:41Z | |
dc.identifier.uri | http://hdl.handle.net/10222/79675 | |
dc.description | Extending TPG to perform real-valued actions. | en_US |
dc.description.abstract | The Tangled Program Graph framework (TPG) is a genetic programming approach to reinforcement learning. Canonical TPG is limited to performing discrete actions. This thesis investigates mechanisms by which TPG might perform real-valued actions. Two approaches are proposed. In the first, a decision-making network extracts state from TPG's internal structure. A gradient-based learning method tailors the network to this representation. In the second, TPG is modified to generate a state representation in an external matrix visible to the decision-making network. No additional learning algorithm is used to configure the decision-making network. Instead, TPG adapts to use the default configuration. This thesis applies these approaches to a modified version of the classic CartPole environment that accepts real-valued actions. This enables the comparison between discrete action configurations of the task and the real-valued formulation. Results indicate that there is no additional complexity in TPG solutions under real-valued action versus discrete action configurations. | en_US |
dc.language.iso | en | en_US |
dc.subject | genetic programming | en_US |
dc.subject | machine learning | en_US |
dc.subject | reinforcement learning | en_US |
dc.title | Providing Real-Valued Actions for Tangled Program Graphs Under the CartPole Benchmark | en_US |
dc.date.defence | 2020-08-14 | |
dc.contributor.department | Faculty of Computer Science | en_US |
dc.contributor.degree | Master of Computer Science | en_US |
dc.contributor.external-examiner | n/a | en_US |
dc.contributor.graduate-coordinator | Michael McAllister | en_US |
dc.contributor.thesis-reader | Nur Zincir-Heywood | en_US |
dc.contributor.thesis-reader | Garnett Wilson | en_US |
dc.contributor.thesis-supervisor | Malcolm Heywood | en_US |
dc.contributor.ethics-approval | Not Applicable | en_US |
dc.contributor.manuscripts | Not Applicable | en_US |
dc.contributor.copyright-release | Not Applicable | en_US |