Active Inference in Multi-Objective Dynamic Environments
| dc.contributor.advisor | Shock, Jonathan | |
| dc.contributor.advisor | Smith, Ryan | |
| dc.contributor.advisor | Solms, Mark | |
| dc.contributor.author | Hodson, Rowan | |
| dc.date.accessioned | 2023-03-07T10:20:53Z | |
| dc.date.available | 2023-03-07T10:20:53Z | |
| dc.date.issued | 2022 | |
| dc.date.updated | 2023-02-20T12:55:54Z | |
| dc.description.abstract | 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. | |
| dc.identifier.apacitation | Hodson, R. (2022). <i>Active Inference in Multi-Objective Dynamic Environments</i>. (). ,Faculty of Science ,Department of Mathematics and Applied Mathematics. Retrieved from http://hdl.handle.net/11427/37304 | en_ZA |
| dc.identifier.chicagocitation | Hodson, Rowan. <i>"Active Inference in Multi-Objective Dynamic Environments."</i> ., ,Faculty of Science ,Department of Mathematics and Applied Mathematics, 2022. http://hdl.handle.net/11427/37304 | en_ZA |
| dc.identifier.citation | Hodson, R. 2022. Active Inference in Multi-Objective Dynamic Environments. . ,Faculty of Science ,Department of Mathematics and Applied Mathematics. http://hdl.handle.net/11427/37304 | en_ZA |
| dc.identifier.ris | TY - Master Thesis AU - Hodson, Rowan AB - 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. DA - 2022_ DB - OpenUCT DP - University of Cape Town KW - Mathematics and Applied Mathematics LK - https://open.uct.ac.za PY - 2022 T1 - Active Inference in Multi-Objective Dynamic Environments TI - Active Inference in Multi-Objective Dynamic Environments UR - http://hdl.handle.net/11427/37304 ER - | en_ZA |
| dc.identifier.uri | http://hdl.handle.net/11427/37304 | |
| dc.identifier.vancouvercitation | Hodson R. Active Inference in Multi-Objective Dynamic Environments. []. ,Faculty of Science ,Department of Mathematics and Applied Mathematics, 2022 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/37304 | en_ZA |
| dc.language.rfc3066 | eng | |
| dc.publisher.department | Department of Mathematics and Applied Mathematics | |
| dc.publisher.faculty | Faculty of Science | |
| dc.subject | Mathematics and Applied Mathematics | |
| dc.title | Active Inference in Multi-Objective Dynamic Environments | |
| dc.type | Master Thesis | |
| dc.type.qualificationlevel | Masters | |
| dc.type.qualificationlevel | MSc |