Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.00044 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912138564468736 |
|---|---|
| author | Moyo, Tofara |
| author_facet | Moyo, Tofara |
| contents | We present a novel method for learning hierarchical abstractions that prioritize competing objectives, leading to improved global expected rewards. Our approach employs a secondary rewarding agent with multiple scalar outputs, each associated with a distinct level of abstraction. The traditional agent then learns to maximize these outputs in a hierarchical manner, conditioning each level on the maximization of the preceding level. We derive an equation that orders these scalar values and the global reward by priority, inducing a hierarchy of needs that informs goal formation. Experimental results on the Pendulum v1 environment demonstrate superior performance compared to a baseline implementation.We achieved state of the art results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_00044 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Creating Hierarchical Dispositions of Needs in an Agent Moyo, Tofara Machine Learning Artificial Intelligence We present a novel method for learning hierarchical abstractions that prioritize competing objectives, leading to improved global expected rewards. Our approach employs a secondary rewarding agent with multiple scalar outputs, each associated with a distinct level of abstraction. The traditional agent then learns to maximize these outputs in a hierarchical manner, conditioning each level on the maximization of the preceding level. We derive an equation that orders these scalar values and the global reward by priority, inducing a hierarchy of needs that informs goal formation. Experimental results on the Pendulum v1 environment demonstrate superior performance compared to a baseline implementation.We achieved state of the art results. |
| title | Creating Hierarchical Dispositions of Needs in an Agent |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2412.00044 |