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.
@article{arxiv.2412.00044,
title = {Creating Hierarchical Dispositions of Needs in an Agent},
author = {Tofara Moyo},
journal= {arXiv preprint arXiv:2412.00044},
year = {2024}
}