---
title: "Discussion on \"Reinforcement Learning: PPO vs. DQN , Who is a Better Mario Player\" | Hashnode"
description: "Discussion on \"Reinforcement Learning: PPO vs. DQN , Who is a Better Mario Player\". Explore reinforcement learning with PPO and DQN algorithms to train AI models for Mario. Follow our journey through 2M timesteps"
url: "https://hashnode.com/posts/reinforcement-learning-ppo-vs-dqn-who-is-a-better-mario-player/6605d7aae9ee059b99f30ecf"
---

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

Discussion

# [Reinforcement Learning: PPO vs. DQN , Who is a Better Mario Player](https://liorshilon.hashnode.dev/reinforcement-learning-ppo-vs-dqn-who-is-a-better-mario-player?utm_source=hashnode&utm_medium=feed)

Explore reinforcement learning with PPO and DQN algorithms to train AI models for Mario. Follow our journey through 2M timesteps

Mar 28, 2024 · 40 min read · liorshilon.hashnode.dev  
Updated Apr 12, 2024  
Read the article

-   [#dqn](https://hashnode.com/tag/dqn)
-   [#reinforcement-learning](https://hashnode.com/tag/reinforcement-learning)
-   [#python](https://hashnode.com/tag/python)
-   [#ai](https://hashnode.com/tag/ai)
-   [#deep-learning](https://hashnode.com/tag/deep-learning)
-   [#data-science](https://hashnode.com/tag/data-science)

## Written by

[Lior Shilon](https://hashnode.com/@liorshilon)

@liorshilon

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

From Bits to Bots: A Developer's Diary

## Responses

Markdown supported · ⌘↵ to post

No responses yet.
