Archive - Reinforcement Learning Diary

My Non-Linear Path to OpenAI - (Part 1 of 2)

A Journey in Endless Curiosity - The Pre-ChatGPT Era

Dec 26, 2025 • Vignesh Ramesh

November 2025

Dissecting a Language Model

What cutting open the different layers of a large language model tell us about its real-self.

Nov 1, 2025 • Vignesh Ramesh

July 2025

The $100 Agents

A new project to train task-specific agents powered by Reinforcement Learning tuned language models with a compute budget of $100.

Jul 13, 2025 • Vignesh Ramesh

The Entropy Conundrum

Post-training with Reinforcement Learning and its impact on the entropy of the model

Jul 7, 2025 • Vignesh Ramesh

Why does RLDiary exist?

Firsthand account of the challenges and insights in applying reinforcement learning to language model–based agents, with a focus on environment design…

Jul 4, 2025 • Vignesh Ramesh

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts