Schoemaker, Jacob (2022) The benefits of Credit Assignment in noisy video game environments. Bachelor's Thesis, Artificial Intelligence.
|
Text
bachelor_project_final.pdf Download (885kB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
toestemming.pdf Restricted to Registered users only Download (120kB) |
Abstract
Both Evolutionary Algorithms (EAs) and Reinforcement Learning Algorithms (RLAs) have proven successful in policy optimisation tasks, but there are very few comparisons of their relative strengths and weaknesses. This makes it difficult to determine which group of algorithms is best suited for a task. This paper presents a comparison of two EAs and two RLAs in Evoman, a new benchmark domain. It compares the algorithms both when there is no variation between environments, and when noise is introduced in the initialisation of the environment. We conclude that whilst EAs reach a similar performance to the RLAs in the static environments, when noise is introduced the credit assignment done by RLAs gives them an edge in modeling the underlying environment.
| Item Type: | Thesis (Bachelor's Thesis) |
|---|---|
| Supervisor name: | Weerd, H.A. de |
| Degree programme: | Artificial Intelligence |
| Thesis type: | Bachelor's Thesis |
| Language: | English |
| Date Deposited: | 11 Mar 2022 12:48 |
| Last Modified: | 11 Mar 2022 12:48 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/26662 |
Actions (login required)
 |
View Item |