Guided belief updates in Deep Bayesian Meta-Reinforcement Learning
| dc.contributor.advisor | Ambrogioni, Luca | |
| dc.contributor.advisor | Hinne, Max | |
| dc.contributor.author | Borker, Jeremy | |
| dc.date.issued | 2022-09-01 | |
| dc.description.abstract | Balancing exploration and exploitation is a key challenge of reinforcement learning. The Bayes-adaptive policy finds this optimal balance by conditioning on a posterior belief over reward and transition function. The current state-of-the-art approach, VariBad, attempts to meta-train a recurrent neural network to perform approximate Bayesian inference over the posterior belief. Observing the posterior variance reveals behavior dissimilar to exact posterior updates. Therefore it appears that learning the desired behavior entirely a posteriori from data is problematic. Hence, this work provides the belief inference model of a Bayesian RL agent with Bayesian inference mechanics a priori and investigate how this influences performance. | |
| dc.identifier.uri | https://theses.ubn.ru.nl/handle/123456789/16314 | |
| dc.language.iso | en | |
| dc.thesis.faculty | Faculteit der Sociale Wetenschappen | |
| dc.thesis.specialisation | specialisations::Faculteit der Sociale Wetenschappen::Artificial Intelligence::Master Artificial Intelligence | |
| dc.thesis.studyprogramme | studyprogrammes::Faculteit der Sociale Wetenschappen::Artificial Intelligence | |
| dc.thesis.type | Master | |
| dc.title | Guided belief updates in Deep Bayesian Meta-Reinforcement Learning |
Files
Original bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- Börker, C. s-4414683-MSc-MKI94-Thesis-2022.pdf
- Size:
- 1.39 MB
- Format:
- Adobe Portable Document Format