Jorritsma, P.H.M. (2011) Incremental Region Enhanced Neural Q-learning for Solving Model-based POMDPs. Bachelor's Thesis, Artificial Intelligence.
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
BaAI-PeterJorritsma-IRENQ.pdf - Other Restricted to Registered users only Download (1MB) |
Abstract
In this paper we compare the ability of the new region-enhanced neural network IRENQ POMDP-solving algorithm to the state of the art Perseus POMDP-solver and the simple Qmdp algorithm. We decided on using 3-dimensional maze problems in addition to larger maze problems than in the earlier paper on the previous version of IRENQ, named RENQ. The results show that IRENQ proved better than Qmdp, but worse than Perseus at solving these POMDPs.
| Item Type: | Thesis (Bachelor's Thesis) |
|---|---|
| Degree programme: | Artificial Intelligence |
| Thesis type: | Bachelor's Thesis |
| Language: | English |
| Date Deposited: | 15 Feb 2018 07:45 |
| Last Modified: | 15 Feb 2018 07:45 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/9586 |
Actions (login required)
 |
View Item |