---
title: "Discussion on \"Why Reward Shaping Sucks and What You Can Do About It\" | Hashnode"
description: "Discussion on \"Why Reward Shaping Sucks and What You Can Do About It\". In my previous article on reward shaping, I walked through four hard-learned lessons about balancing collision penalties in a navigation task. I eventually found the \"Goldilocks solution\" - a -0.1 penalty that let my agent learn to navigate obstacles..."
url: "https://hashnode.com/posts/why-reward-shaping-sucks-and-what-you-can-do-about-it/68cc74dc67e19b628e202331"
---

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

Discussion

# [Why Reward Shaping Sucks and What You Can Do About It](https://proximal.hashnode.dev/why-reward-shaping-sucks-and-what-you-can-do-about-it?utm_source=hashnode&utm_medium=feed)

In my previous article on reward shaping, I walked through four hard-learned lessons about balancing collision penalties in a navigation task. I eventually found the "Goldilocks solution" - a -0.1 penalty that let my agent learn to navigate obstacles...

Sep 18, 2025 · 6 min read · proximal.hashnode.dev  
Read the article

-   [#ai](https://hashnode.com/tag/ai)
-   [#bellman-equation](https://hashnode.com/tag/bellman-equation)
-   [#deep-learning](https://hashnode.com/tag/deep-learning)
-   [#machine-learning](https://hashnode.com/tag/machine-learning)
-   [#reinforcement-learning](https://hashnode.com/tag/reinforcement-learning)
-   [#reward-shaping](https://hashnode.com/tag/reward-shaping)

## Written by

[Duane Nielsen](https://hashnode.com/@duanerocks)

@duanerocks

  
[View profile](https://hashnode.com/@duanerocks)

Obsessed with RL

## Responses 1

Markdown supported · ⌘↵ to post

[Revan wjy](https://hashnode.com/@Revanwjy)

[Sep 19, 2025](https://hashnode.com/posts/why-reward-shaping-sucks-and-what-you-can-do-about-it/68cc74dc67e19b628e202331/comment/68cd0f3536ae1c72a642e782)

Nyatai disini dapat cuan

jo777.help
