Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Trends, problems, and solutions in causality and reinforcement learning
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 cau...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | Eng |
| Published: |
Department of Mathematics and Applied Mathematics
2025
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613268133019648 |
|---|---|
| access_status_str | Open Access |
| author | Grimbly, St John |
| author2 | Shock, Jonathan |
| author_browse | Grimbly, St John Shock, Jonathan |
| author_facet | Shock, Jonathan Grimbly, St John |
| author_sort | Grimbly, St John |
| collection | Thesis |
| description | 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. |
| format | Thesis |
| id | oai:open.uct.ac.za:11427/40948 |
| institution | University of Cape Town (South Africa) |
| language | Eng |
| last_indexed | 2026-06-10T12:33:26.520Z |
| license_str | Not specified — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from UCTD — University of Cape Town Open Access Repository |
| publishDate | 2025 |
| publishDateRange | 2025 |
| publishDateSort | 2025 |
| publisher | Department of Mathematics and Applied Mathematics |
| publisherStr | Department of Mathematics and Applied Mathematics |
| record_format | dspace |
| source_str | UCTD — University of Cape Town Open Access Repository |
| spelling | oai:open.uct.ac.za:11427/40948 Trends, problems, and solutions in causality and reinforcement learning Grimbly, St John Shock, Jonathan Mathematics and Applied Mathematics 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. 2025-02-13T13:12:10Z 2025-02-13T13:12:10Z 2024 2025-02-13T13:03:10Z Thesis / Dissertation Masters MSc http://hdl.handle.net/11427/40948 Eng application/pdf Department of Mathematics and Applied Mathematics Faculty of Science University of Cape Town |
| spellingShingle | Mathematics and Applied Mathematics Grimbly, St John Trends, problems, and solutions in causality and reinforcement learning |
| thesis_degree_str | Master's |
| title | Trends, problems, and solutions in causality and reinforcement learning |
| title_full | Trends, problems, and solutions in causality and reinforcement learning |
| title_fullStr | Trends, problems, and solutions in causality and reinforcement learning |
| title_full_unstemmed | Trends, problems, and solutions in causality and reinforcement learning |
| title_short | Trends, problems, and solutions in causality and reinforcement learning |
| title_sort | trends problems and solutions in causality and reinforcement learning |
| topic | Mathematics and Applied Mathematics |
| url | http://hdl.handle.net/11427/40948 |
| work_keys_str_mv | AT grimblystjohn trendsproblemsandsolutionsincausalityandreinforcementlearning |