Study Reinforcement Learning

start library curriculum watch about

quick reference

Cheat sheets

Quick reference: formulas, losses, KL control, and the training loops side by side.

KL control in RL: cheat sheet
RL-for-LLM training loops: 2024/2025 map
Deep RL Mathematical Formulas - Quick Reference
Deep RL Quick Reference & Cheat Sheet
RL loss functions: cheat sheet
RLHF vs DPO vs GRPO vs RLVR: cheat sheet

Study notes by Yad Konrad, started on 31 December 2016 as a list of talks and courses. Every lecture is marked unreviewed until a person has checked it. About and credit.

home start library curriculum watch about notes releases github

Version 0.3.0, built from the study repo at 1b7eae8 (2026-11-03). Text licensed under Creative Commons BY-NC-ND. Set in Alegreya. Built with Mycelium and Astro.

ESC

Quick Actions

Browse all notes

Knowledge Graph

34 notes · 66 connections

Foundations

Classical RL

RLHF

RLAIF

RLVR and reasoning

Agentic RL

Offline RL

Systems

Drag to move · Scroll to zoom · Click to navigate