Transfer Learning for Customized Car Racing Environments
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910231700701184 |
|---|---|
| author | Arockiaraj, Benedict Florance Chang, Richard Yee, Wesley |
| author_facet | Arockiaraj, Benedict Florance Chang, Richard Yee, Wesley |
| contents | Transfer Learning, a technique where a model/agent can use the knowledge/expertise that it gained from one task and exploit that to solve another closely-related task, is often used in tackling problems in deep learning. Through this project, we explore transfer learning in the purview of deep reinforcement learning. Specifically, we want to use transfer learning to achieve the fast lap times in OpenAI's Car racing environment by training the agent on one circuit, and racing it on other customized target environments by zero-shot transfer or by additional fine-tuning. In addition, we compare the performance of model-based and model-free approaches, and observe that model-based approaches dominate in performance and converge faster than model-free approaches in this environment. We observe that transfer learning in most setups not only boosts the performance on the target domain, but also shows high performance ability during learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_17928 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Transfer Learning for Customized Car Racing Environments Arockiaraj, Benedict Florance Chang, Richard Yee, Wesley Robotics Machine Learning Transfer Learning, a technique where a model/agent can use the knowledge/expertise that it gained from one task and exploit that to solve another closely-related task, is often used in tackling problems in deep learning. Through this project, we explore transfer learning in the purview of deep reinforcement learning. Specifically, we want to use transfer learning to achieve the fast lap times in OpenAI's Car racing environment by training the agent on one circuit, and racing it on other customized target environments by zero-shot transfer or by additional fine-tuning. In addition, we compare the performance of model-based and model-free approaches, and observe that model-based approaches dominate in performance and converge faster than model-free approaches in this environment. We observe that transfer learning in most setups not only boosts the performance on the target domain, but also shows high performance ability during learning. |
| title | Transfer Learning for Customized Car Racing Environments |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2605.17928 |