Graceful task adaptation with a bi-hemispheric RL agent
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_ | 1866913432679219200 |
|---|---|
| author | Nicholas, Grant Kuhlmann, Levin Kowadlo, Gideon |
| author_facet | Nicholas, Grant Kuhlmann, Levin Kowadlo, Gideon |
| contents | In humans, responsibility for performing a task gradually shifts from the right hemisphere to the left. The Novelty-Routine Hypothesis (NRH) states that the right and left hemispheres are used to perform novel and routine tasks respectively, enabling us to learn a diverse range of novel tasks while performing the task capably. Drawing on the NRH, we develop a reinforcement learning agent with specialised hemispheres that can exploit generalist knowledge from the right-hemisphere to avoid poor initial performance on novel tasks. In addition, we find that this design has minimal impact on its ability to learn novel tasks. We conclude by identifying improvements to our agent and exploring potential expansion to the continual learning setting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_11456 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Graceful task adaptation with a bi-hemispheric RL agent Nicholas, Grant Kuhlmann, Levin Kowadlo, Gideon Machine Learning Artificial Intelligence I.2.0; I.2.6 In humans, responsibility for performing a task gradually shifts from the right hemisphere to the left. The Novelty-Routine Hypothesis (NRH) states that the right and left hemispheres are used to perform novel and routine tasks respectively, enabling us to learn a diverse range of novel tasks while performing the task capably. Drawing on the NRH, we develop a reinforcement learning agent with specialised hemispheres that can exploit generalist knowledge from the right-hemisphere to avoid poor initial performance on novel tasks. In addition, we find that this design has minimal impact on its ability to learn novel tasks. We conclude by identifying improvements to our agent and exploring potential expansion to the continual learning setting. |
| title | Graceful task adaptation with a bi-hemispheric RL agent |
| topic | Machine Learning Artificial Intelligence I.2.0; I.2.6 |
| url | https://arxiv.org/abs/2407.11456 |