Skip to content
Back to skills

Functional Regularization For Reinforcement Learning Via Learned Fourier Features

ASecurity

**arXiv ID:** 2112.03257 **Authors:** Alexander C. Li, Deepak Pathak **Published:** 2021-12-06T18:59:52Z **Abstract:** We propose a simple architecture for deep reinforcement learning by embedding inputs into a learned Fourier basis and show that it improves the sample efficiency of both state-based and image-based RL. We perform infinite-width analysis of our architecture using the Neural Tangent Kernel and theoretically show that tuning the initial variance of the Fourier basis is equivalen...

  • 3 stars
  • 0 votes
  • 0 copies
  • 4 views
  • Added September 11, 2026
toolsperformance

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill functional-regularization-for-reinforcement-learning-via-learned-fourier-features --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Functional Regularization For Reinforcement Learning Via Learned Fourier Features?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Functional Regularization For Reinforcement Learning Via Learned Fourier Features
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-functional-regularization-for-reinforcement-learni/badge)](https://www.skillsdirectory.com/skills/hiyenwong-functional-regularization-for-reinforcement-learni)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# Functional Regularization for Reinforcement Learning via Learned Fourier Features

**arXiv ID:** 2112.03257
**Authors:** Alexander C. Li, Deepak Pathak
**Published:** 2021-12-06T18:59:52Z
**Abstract:**
We propose a simple architecture for deep reinforcement learning by embedding inputs into a learned Fourier basis and show that it improves the sample efficiency of both state-based and image-based RL. We perform infinite-width analysis of our architecture using the Neural Tangent Kernel and theoretically show that tuning the initial variance of the Fourier basis is equivalent to functional regularization of the learned deep network. That is, these learned Fourier features allow for adjusting the degree to which networks underfit or overfit different frequencies in the training data, and hence provide a controlled mechanism to improve the stability and performance of RL optimization. Empirically, this allows us to prioritize learning low-frequency functions and speed up learning by reducing networks' susceptibility to noise in the optimization process, such as during Bellman updates. Experiments on standard state-based and image-based RL benchmarks show clear benefits of our architecture over the baselines. Website at https://alexanderli.com/learned-fourier-features

## Skill Description

This skill is generated from the arXiv paper: Functional Regularization for Reinforcement Learning via Learned Fourier Features (2112.03257).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2112.03257](http://arxiv.org/abs/2112.03257v1)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in tools →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.