# Cascade Attribute Network: Decomposing Reinforcement Learning Control Policies using Hierarchical Neural Networks

arXiv: https://arxiv.org/abs/2005.04213 · HTML: https://mlsanity.com/paper/2005.04213/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2020.

## Built on by (most cited first, 4 of 4)

- [Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs](https://mlsanity.com/paper/2407.07775/) (2024)
- [MATRIX: Multi-Agent Trajectory Generation with Diverse Contexts](https://mlsanity.com/paper/2403.06041/) (2024)
- [A Learning Approach for Joint Design of Event-triggered Control and Power-Efficient Resource Allocation](https://mlsanity.com/paper/2205.07070/) (2022)
- [History Encoding Representation Design for Human Intention Inference](https://mlsanity.com/paper/2106.02222/) (2021)

## Abstract (arXiv)

Reinforcement learning methods have been developed to achieve great success in training control policies in various automation tasks. However, a main challenge of the wider application of reinforcement learning in practical automation is that the training process is hard and the pretrained policy networks are hardly reusable in other similar cases. To address this problem, we propose the cascade attribute network (CAN), which utilizes its hierarchical structure to decompose a complicated control policy in terms of the requirement constraints, which we call attributes, encoded in the control tasks. We validated the effectiveness of our proposed method on two robot control scenarios with various add-on attributes. For some control tasks with more than one add-on attribute attribute, by directly assembling the attribute modules in cascade, the CAN can provide ideal control policies in a zero-shot manner.