dc.contributor.author | Al Masalma, Mihyar | |
dc.date.accessioned | 2022-04-01T12:59:23Z | |
dc.date.available | 2022-04-01T12:59:23Z | |
dc.date.issued | 2022-04-01T12:59:23Z | |
dc.identifier.uri | http://hdl.handle.net/10222/81503 | |
dc.description.abstract | Partially observable tasks require a learning agent to make decisions based on the previous state, hence a requirement for memory. There is a trade-off between the flexibility and specificity of the memory. This impacts the ability of the agent to solve specific tasks versus generalize to a range of tasks. Recently, a suite of `deep memory tasks’ was proposed to evaluate different approaches to partially observable problems. In this thesis, a canonical tree-structured genetic programming (GP) framework is assumed as the starting point, with memory taking the form of a list. The interface to memory requires that canonical GP is deployed as a modular co-evolutionary framework to support multiple outputs. An empirical evaluation is performed using three deep memory benchmarks to showcase the relative strength/weaknesses of this approach. We also compare our findings with neural solutions to distinguish between the relative contribution of GP versus list-based memory. | en_US |
dc.language.iso | en | en_US |
dc.subject | NEAT | en_US |
dc.subject | GP | en_US |
dc.subject | Deep Memory | en_US |
dc.subject | Genetic Programming | en_US |
dc.subject | Memory Tasks | en_US |
dc.subject | External Memory | en_US |
dc.title | Benchmarking Modular Genetic Programming on Deep Memory Tasks | en_US |
dc.date.defence | 2022-03-21 | |
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 |