Enhancing Analogical Reasoning in the Abstraction and Reasoning Corpus via Model-Based RL
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916371030343680 |
|---|---|
| author | Lee, Jihwan Sim, Woochang Kim, Sejin Kim, Sundong |
| author_facet | Lee, Jihwan Sim, Woochang Kim, Sejin Kim, Sundong |
| contents | This paper demonstrates that model-based reinforcement learning (model-based RL) is a suitable approach for the task of analogical reasoning. We hypothesize that model-based RL can solve analogical reasoning tasks more efficiently through the creation of internal models. To test this, we compared DreamerV3, a model-based RL method, with Proximal Policy Optimization, a model-free RL method, on the Abstraction and Reasoning Corpus (ARC) tasks. Our results indicate that model-based RL not only outperforms model-free RL in learning and generalizing from single tasks but also shows significant advantages in reasoning across similar tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_14855 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Analogical Reasoning in the Abstraction and Reasoning Corpus via Model-Based RL Lee, Jihwan Sim, Woochang Kim, Sejin Kim, Sundong Artificial Intelligence Logic in Computer Science This paper demonstrates that model-based reinforcement learning (model-based RL) is a suitable approach for the task of analogical reasoning. We hypothesize that model-based RL can solve analogical reasoning tasks more efficiently through the creation of internal models. To test this, we compared DreamerV3, a model-based RL method, with Proximal Policy Optimization, a model-free RL method, on the Abstraction and Reasoning Corpus (ARC) tasks. Our results indicate that model-based RL not only outperforms model-free RL in learning and generalizing from single tasks but also shows significant advantages in reasoning across similar tasks. |
| title | Enhancing Analogical Reasoning in the Abstraction and Reasoning Corpus via Model-Based RL |
| topic | Artificial Intelligence Logic in Computer Science |
| url | https://arxiv.org/abs/2408.14855 |