The development of action repertoires for humanoid robot behavior
| dc.contributor.advisor | Kwisthout, Johan | |
| dc.contributor.author | Bergman, Tim | |
| dc.contributor.author | Rutar, Rutar | |
| dc.date.issued | 2019-02-21 | |
| dc.description.abstract | The predictive processing account of neuroscience views the brain as a prediction-making and hypothesis-testing machine based on a hierarchically-organized series of generative models. The brain makes predictions about the world, and then seeks to resolve the error between them and observed reality. One of the ways in which it may do so is denoted as active inference: by acting on the world based on a model describing the actions’ effects such that the observed state now matches a wanted state. How these models are formed and adapted during infancy, however, is not yet known. In this exploratory study we investigated a possible computational strategy for creating an action repertoire for use in a humanoid robotic agent, adapting it to become more or less fine grained, whilst transferring previously learnt information. For this, we used an implementation based on clustering and Q-learning, and transferring previously learnt Q-values between clusterings of varying granularity. We tested its performance in a virtual reaching task based on visual and motor data gathered from a NAO robot. Our final results show that our proposed method of Remapping of Q-values ("ReQ-ing") allows the agent to learn fine-tuned actions to its performance plateau faster, but at the same time, doesn’t allow the agent to learn to a lower error over-all compared to those agent that do not use this method. Other observations are that reward functions should also be properly adapted to predispose a more fine-tuned model, and that the addition of additional axes of control should also be reflected in clustering and an agent’s reward function. | en_US |
| dc.embargo.lift | 10000-01-01 | |
| dc.embargo.type | Permanent embargo | en_US |
| dc.identifier.uri | https://theses.ubn.ru.nl/handle/123456789/10691 | |
| dc.language.iso | en | en_US |
| dc.thesis.faculty | Faculteit der Sociale Wetenschappen | en_US |
| dc.thesis.specialisation | Master Artificial Intelligence | en_US |
| dc.thesis.studyprogramme | Artificial Intelligence | en_US |
| dc.thesis.type | Master | en_US |
| dc.title | The development of action repertoires for humanoid robot behavior | en_US |
Files
Original bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- S3012050_BergmanT2018.pdf
- Size:
- 4.67 MB
- Format:
- Adobe Portable Document Format