Trends, problems, and solutions in causality and reinforcement learning

dc.contributor.advisorShock, Jonathan
dc.contributor.authorGrimbly, St John
dc.date.accessioned2025-02-13T13:12:10Z
dc.date.available2025-02-13T13:12:10Z
dc.date.issued2024
dc.date.updated2025-02-13T13:03:10Z
dc.description.abstractThis thesis reviews, examines, and investigates the trends in the fields of causality and in reinforcement learning (RL). Theory is developed for both active research areas, with a specific focus on the overlap in underlying theory. The core argument is that the RL problem can be formulated as a causal problem, where the agent is learning causal policies that maximise return (via some causal relationship implied by the policy) and does this via selecting optimal actions (performing interventions) in the environment. Although relevant in both model-based and model-free scenarios, focus is placed on model-based modalities where one can view the various models as being causal models. It is further argued that this reformulation enables various theoretical improvements in reasoning ability for a learning agent, and does this while offering improved efficiency, interpretability, robustness, and generalisation across various learning modalities. As an application of the causal methods discussed, we also investigate whether applied causal discovery can lead to disparate impacts on sensitive subgroups. Finally, we reflect on the findings, highlight open problems, and propose future research directions.
dc.identifier.apacitationGrimbly, S. J. (2024). <i>Trends, problems, and solutions in causality and reinforcement learning</i>. (). University of Cape Town ,Faculty of Science ,Department of Mathematics and Applied Mathematics. Retrieved from http://hdl.handle.net/11427/40948en_ZA
dc.identifier.chicagocitationGrimbly, St John. <i>"Trends, problems, and solutions in causality and reinforcement learning."</i> ., University of Cape Town ,Faculty of Science ,Department of Mathematics and Applied Mathematics, 2024. http://hdl.handle.net/11427/40948en_ZA
dc.identifier.citationGrimbly, S.J. 2024. Trends, problems, and solutions in causality and reinforcement learning. . University of Cape Town ,Faculty of Science ,Department of Mathematics and Applied Mathematics. http://hdl.handle.net/11427/40948en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Grimbly, St John AB - This thesis reviews, examines, and investigates the trends in the fields of causality and in reinforcement learning (RL). Theory is developed for both active research areas, with a specific focus on the overlap in underlying theory. The core argument is that the RL problem can be formulated as a causal problem, where the agent is learning causal policies that maximise return (via some causal relationship implied by the policy) and does this via selecting optimal actions (performing interventions) in the environment. Although relevant in both model-based and model-free scenarios, focus is placed on model-based modalities where one can view the various models as being causal models. It is further argued that this reformulation enables various theoretical improvements in reasoning ability for a learning agent, and does this while offering improved efficiency, interpretability, robustness, and generalisation across various learning modalities. As an application of the causal methods discussed, we also investigate whether applied causal discovery can lead to disparate impacts on sensitive subgroups. Finally, we reflect on the findings, highlight open problems, and propose future research directions. DA - 2024 DB - OpenUCT DP - University of Cape Town KW - Mathematics and Applied Mathematics LK - https://open.uct.ac.za PB - University of Cape Town PY - 2024 T1 - Trends, problems, and solutions in causality and reinforcement learning TI - Trends, problems, and solutions in causality and reinforcement learning UR - http://hdl.handle.net/11427/40948 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/40948
dc.identifier.vancouvercitationGrimbly SJ. Trends, problems, and solutions in causality and reinforcement learning. []. University of Cape Town ,Faculty of Science ,Department of Mathematics and Applied Mathematics, 2024 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/40948en_ZA
dc.language.rfc3066Eng
dc.publisher.departmentDepartment of Mathematics and Applied Mathematics
dc.publisher.facultyFaculty of Science
dc.publisher.institutionUniversity of Cape Town
dc.subjectMathematics and Applied Mathematics
dc.titleTrends, problems, and solutions in causality and reinforcement learning
dc.typeThesis / Dissertation
dc.type.qualificationlevelMasters
dc.type.qualificationlevelMSc
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
thesis_sci_2024_grimbly st john.pdf
Size:
4.23 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.72 KB
Format:
Item-specific license agreed upon to submission
Description:
Collections