Kosters, Tom (2022) On the presence of Winning Tickets in Reinforcement Learning. Bachelor's Thesis, Artificial Intelligence.
|
Text
thesis_kosters_s3228592.pdf Download (1MB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
toestemming.pdf Restricted to Registered users only Download (96kB) |
Abstract
The lottery ticket hypothesis suggests that randomly-initialized neural networks contain smaller sub-networks that can be trained to perform at least as well as the full network. This project demonstrates that such winning tickets can be found in shallow neural networks used for function approximation in simple reinforcement learning tasks, and that they are found across environments, algorithms and pruning strategies.
| Item Type: | Thesis (Bachelor's Thesis) |
|---|---|
| Supervisor name: | Sabatelli, M. |
| Degree programme: | Artificial Intelligence |
| Thesis type: | Bachelor's Thesis |
| Language: | English |
| Date Deposited: | 21 Apr 2022 08:57 |
| Last Modified: | 21 Apr 2022 08:57 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/26958 |
Actions (login required)
 |
View Item |