Reinforcement Learning With Chromatic Networks For Compact Architecture Search
ASecurity**arXiv ID:** 1907.06511 **Authors:** Xingyou Song, Krzysztof Choromanski, Jack Parker-Holder, Yunhao Tang, Wenbo Gao, Aldo Pacchiano, Tamas Sarlos, Deepali Jain, Yuxiang Yang **Published:** 2019-07-10T16:57:50Z **Abstract:** We present a neural architecture search algorithm to construct compact reinforcement learning (RL) policies, by combining ENAS and ES in a highly scalable and intuitive way. By defining the combinatorial search space of NAS to be the set of different edge-partitionings (...
- 3 stars
- 0 votes
- 0 copies
- 4 views
- Added September 11, 2026
Security analysis
100/100npx -y skills add hiyenwong/ai_collection --skill reinforcement-learning-with-chromatic-networks-for-compact-architecture-search --agent claude-codeAre you the author of Reinforcement Learning With Chromatic Networks For Compact Architecture Search?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-reinforcement-learning-with-chromatic-networks-for)# Reinforcement Learning with Chromatic Networks for Compact Architecture Search
**arXiv ID:** 1907.06511
**Authors:** Xingyou Song, Krzysztof Choromanski, Jack Parker-Holder, Yunhao Tang, Wenbo Gao, Aldo Pacchiano, Tamas Sarlos, Deepali Jain, Yuxiang Yang
**Published:** 2019-07-10T16:57:50Z
**Abstract:**
We present a neural architecture search algorithm to construct compact reinforcement learning (RL) policies, by combining ENAS and ES in a highly scalable and intuitive way. By defining the combinatorial search space of NAS to be the set of different edge-partitionings (colorings) into same-weight classes, we represent compact architectures via efficient learned edge-partitionings. For several RL tasks, we manage to learn colorings translating to effective policies parameterized by as few as $17$ weight parameters, providing >90% compression over vanilla policies and 6x compression over state-of-the-art compact policies based on Toeplitz matrices, while still maintaining good reward. We believe that our work is one of the first attempts to propose a rigorous approach to training structured neural network architectures for RL problems that are of interest especially in mobile robotics with limited storage and computational resources.
## Skill Description
This skill is generated from the arXiv paper: Reinforcement Learning with Chromatic Networks for Compact Architecture Search (1907.06511).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:1907.06511](http://arxiv.org/abs/1907.06511v4)
Attribution
Related skills
View all in tools →Comments
Loading comments…
Newsletter
Get the weekly list of safe new skills, and the ones we pulled.