Designing and implementing a survival agent using reinforcement learning in Unity
| dc.contributor.advisor | Bogacsovics, Gergő | |
| dc.contributor.author | Khandoker, Riman Faradis | |
| dc.contributor.department | DE--Informatikai Kar | |
| dc.date.accessioned | 2026-02-12T18:29:06Z | |
| dc.date.available | 2026-02-12T18:29:06Z | |
| dc.date.created | 2025 | |
| dc.description.abstract | This thesis explores reinforcement learning in a Unity environment, moving step by step from simple energy collection to complex obstacle avoidance. It uses Unity ML‑Agents to train agents and tests how reward design affects learning. The project shows that small mistakes in rewards can cause unusual behaviors, like the agent freezing or crashing on purpose. Through iterative tuning and debugging, high‑performing agents with high success rates across all levels was achieved. Overall, the thesis showcases strong technical execution, clear documentation of challenges, and valuable insights into designing adaptive and interpretable RL training setups. | |
| dc.description.course | Programtervező informatikus | |
| dc.description.degree | BSc/BA | |
| dc.format.extent | 54 | |
| dc.identifier.uri | https://hdl.handle.net/2437/404429 | |
| dc.language.iso | en | |
| dc.rights.info | Hozzáférhető a 2022 decemberi felsőoktatási törvénymódosítás értelmében. | |
| dc.subject | Reinforcement Learning | |
| dc.subject | Unity ML‑Agents | |
| dc.subject.dspace | Informatics::Computer Science | |
| dc.title | Designing and implementing a survival agent using reinforcement learning in Unity |
Fájlok
Eredeti köteg (ORIGINAL bundle)
1 - 1 (Összesen 1)
Nincs kép
- Név:
- thesis.pdf
- Méret:
- 3.44 MB
- Formátum:
- Adobe Portable Document Format
- Leírás:
- thesis
Engedélyek köteg
1 - 1 (Összesen 1)
Nincs kép
- Név:
- license.txt
- Méret:
- 1.95 KB
- Formátum:
- Item-specific license agreed upon to submission
- Leírás: