---
title: Scaling RL for LLMs — Slides
emoji: 📈
colorFrom: green
colorTo: purple
sdk: static
app_file: index.html
pinned: false
license: mit
short_description: Scaling RL for LLMs — AMD AI Dev Day slides
---

# Scaling RL for LLMs — RL Environments and RL Training

Talk slides by [Adithya S Kolavi](https://huggingface.co/AdithyaSK), presented at
**[AMD AI Dev Day](https://amd.indiadevday.com/)**.

RL environments (OpenEnv) and RL training (TRL) — what an environment actually is,
how reward hacking happens, and how to build and train against your own.

React + Vite. Arrow keys / clicker / swipe to navigate, `t` for light/dark, `f` for fullscreen.

Source: [adithya-s-k/RL_Envs_101](https://github.com/adithya-s-k/RL_Envs_101) →
`tutorials/slides/rl-environments-101-amd/`