Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Active Inference in Multi-Objective Dynamic Environments
Artificial Intelligence holds the promise of not only creating intelligent entities, but also unlocking the mysteries of our brains, and the nature of the subjective consciousness that accompanies them. Many paradigms of artificial intelligence are attempting to push the boundaries of the field, in...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
Department of Mathematics and Applied Mathematics
2023
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867614036212842496 |
|---|---|
| access_status_str | Open Access |
| author | Hodson, Rowan |
| author2 | Shock, Jonathan |
| author_browse | Hodson, Rowan Shock, Jonathan |
| author_facet | Shock, Jonathan Hodson, Rowan |
| author_sort | Hodson, Rowan |
| collection | Thesis |
| description | Artificial Intelligence holds the promise of not only creating intelligent entities, but also unlocking the mysteries of our brains, and the nature of the subjective consciousness that accompanies them. Many paradigms of artificial intelligence are attempting to push the boundaries of the field, in order to catch a glimpse of the secrets behind general intelligence and the nature of the human mind. A less explored, yet promising paradigm is that of Active Inference - a theory which details a first-principled explanation of how agents use action and perception to successfully operate within an external environment. Much work has been done to explore the framework's viability in modelling scenarios both related to neural process theory and more classical agent-based machine learning. However, due to the relative recency of the theory, there are still many areas of comparison and evaluation to explore. This dissertation aims to investigate Active Inference's algorithmic capacity to solve more complex decision-based environments. Specifically, with varying degrees of complexity, I make use of a dynamic environment with a multi-objective reward function to investigate the Active Inference agent's ability to learn and plan while balancing exploration and exploitation, and compare this to other Bayesian Machine Learning algorithms. In doing so, I investigate some novel approaches and additions to Active Inference's algorithmic structure which include a dynamic preference distribution, a two-tiered hierarchical approach to the state space (using model-free Reinforcement Learning to solve the lower level), and the introduction of the Propagated Parameter Belief Search algorithm - a modification to Active Inference which allows the agent to perform more complex counterfactual reasoning. |
| format | Thesis |
| id | oai:open.uct.ac.za:11427/37304 |
| institution | University of Cape Town (South Africa) |
| language | eng |
| last_indexed | 2026-06-10T12:45:39.296Z |
| license_str | Not specified — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from UCTD — University of Cape Town Open Access Repository |
| publishDate | 2023 |
| publishDateRange | 2023 |
| publishDateSort | 2023 |
| 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:11427/37304 Active Inference in Multi-Objective Dynamic Environments Hodson, Rowan Shock, Jonathan Smith, Ryan Solms, Mark Mathematics and Applied Mathematics Artificial Intelligence holds the promise of not only creating intelligent entities, but also unlocking the mysteries of our brains, and the nature of the subjective consciousness that accompanies them. Many paradigms of artificial intelligence are attempting to push the boundaries of the field, in order to catch a glimpse of the secrets behind general intelligence and the nature of the human mind. A less explored, yet promising paradigm is that of Active Inference - a theory which details a first-principled explanation of how agents use action and perception to successfully operate within an external environment. Much work has been done to explore the framework's viability in modelling scenarios both related to neural process theory and more classical agent-based machine learning. However, due to the relative recency of the theory, there are still many areas of comparison and evaluation to explore. This dissertation aims to investigate Active Inference's algorithmic capacity to solve more complex decision-based environments. Specifically, with varying degrees of complexity, I make use of a dynamic environment with a multi-objective reward function to investigate the Active Inference agent's ability to learn and plan while balancing exploration and exploitation, and compare this to other Bayesian Machine Learning algorithms. In doing so, I investigate some novel approaches and additions to Active Inference's algorithmic structure which include a dynamic preference distribution, a two-tiered hierarchical approach to the state space (using model-free Reinforcement Learning to solve the lower level), and the introduction of the Propagated Parameter Belief Search algorithm - a modification to Active Inference which allows the agent to perform more complex counterfactual reasoning. 2023-03-07T10:20:53Z 2023-03-07T10:20:53Z 2022 2023-02-20T12:55:54Z Master Thesis Masters MSc http://hdl.handle.net/11427/37304 eng application/pdf Department of Mathematics and Applied Mathematics Faculty of Science |
| spellingShingle | Mathematics and Applied Mathematics Hodson, Rowan Active Inference in Multi-Objective Dynamic Environments |
| thesis_degree_str | Master's |
| title | Active Inference in Multi-Objective Dynamic Environments |
| title_full | Active Inference in Multi-Objective Dynamic Environments |
| title_fullStr | Active Inference in Multi-Objective Dynamic Environments |
| title_full_unstemmed | Active Inference in Multi-Objective Dynamic Environments |
| title_short | Active Inference in Multi-Objective Dynamic Environments |
| title_sort | active inference in multi objective dynamic environments |
| topic | Mathematics and Applied Mathematics |
| url | http://hdl.handle.net/11427/37304 |
| work_keys_str_mv | AT hodsonrowan activeinferenceinmultiobjectivedynamicenvironments |