---
title: "Discussion on \"[Paper Review] DeepSeek-R1 Incentivizing Reasoning Capability in LLMs via Reinforcement Learning\" | Hashnode"
description: "Discussion on \"[Paper Review] DeepSeek-R1 Incentivizing Reasoning Capability in LLMs via Reinforcement Learning\". DeepSeek-R1 uses reinforcement learning to enhance reasoning in language models, outperforming peers with innovative training methods"
url: "https://hashnode.com/posts/paper-review-deepseek-r1-incentivizing-reasoning-capability-in-llms-via-reinforcement-learning/6804e46684aed2abb1bad4cf"
---

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

Discussion

# [\[Paper Review\] DeepSeek-R1 Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://ramieeee.me/paper-review-deepseek-r1-incentivizing-reasoning-capability-in-llms-via-reinforcement-learning?utm_source=hashnode&utm_medium=feed)

DeepSeek-R1 uses reinforcement learning to enhance reasoning in language models, outperforming peers with innovative training methods

Apr 20, 2025 · 6 min read · ramieeee.me  
Updated Apr 27, 2025  
Read the article

-   [#deepseek](https://hashnode.com/tag/deepseek)
-   [#llm](https://hashnode.com/tag/llm)
-   [#reinforcement-learning](https://hashnode.com/tag/reinforcement-learning)

## Written by

[Ramhee Yeon](https://hashnode.com/@ramieeee)

@ramieeee · Seoul, South Korea

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

AI researcher and developer

South Korean, master's degree of AI. A research focused AI specialist, and a rogrammer for LLM. I am seeking opportunities worldwide. I used to live in Frankfurt, Moscow, Pretoria, Baguio. Where to next?

## Responses

Markdown supported · ⌘↵ to post

No responses yet.