Bornemann, Lennard (2022) The Lottery Ticket Hypothesis in Deep Reinforcement Learning. Bachelor's Thesis, Artificial Intelligence.
|
Text
bAI_2022_BornemannLR.pdf Download (437kB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
toestemming.pdf Restricted to Registered users only Download (117kB) |
Abstract
Previous research suggests the existence of small sub-networks within convolutional neural networks which perform just as well as their original non-pruned counterpart. Such im- plication has wide reaching impact, as it suggests that any neural network can produce such sub-networks, known as winning lottery tickets. The existence of such winning tickets in all fields of machine learning is a promising idea, as it could allow for the spacial and computational reduction of any machine learning task. This paper aims to investigate the existence of such winning lottery tickets within the field of deep reinforcement learning, specifically within deep Q-networks.
| Item Type: | Thesis (Bachelor's Thesis) |
|---|---|
| Supervisor name: | Sabatelli, M. |
| Degree programme: | Artificial Intelligence |
| Thesis type: | Bachelor's Thesis |
| Language: | English |
| Date Deposited: | 19 Apr 2022 10:00 |
| Last Modified: | 19 Apr 2022 10:00 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/26911 |
Actions (login required)
 |
View Item |