---
title: "Discussion on \"The reward is part of the dataset\" | Hashnode"
description: "Discussion on \"The reward is part of the dataset\". Six wrong normalization formulas passed a CPU checker with identity inputs. What this means for kernel RL feedback and held-out evaluation."
url: "https://hashnode.com/posts/the-reward-is-part-of-the-dataset/6af192e0befea3fedc931883"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [The reward is part of the dataset](https://nodus-compute.hashnode.dev/the-reward-is-part-of-the-dataset?utm_source=hashnode&utm_medium=feed)

Six wrong normalization formulas passed a CPU checker with identity inputs. What this means for kernel RL feedback and held-out evaluation.

2d ago · 3 min read · nodus-compute.hashnode.dev  
Read the article

-   [#machine-learning](https://hashnode.com/tag/machine-learning)
-   [#reinforcement-learning](https://hashnode.com/tag/reinforcement-learning)
-   [#gpu](https://hashnode.com/tag/gpu)

## Written by

[Viswaretas Kotra](https://hashnode.com/@viswa-kotra)

@viswa-kotra · San Francisco, USA

  
[View profile](https://hashnode.com/@viswa-kotra)

Founder @ Nodus Compute, previously in HFT, Distributed Systems, and AI.

Founder @ Nodus Compute

## Responses

Markdown supported · ⌘↵ to post

No responses yet.