Reinforcement Learning

GRPO achieves the lowest aggregate sycophancy (0.169) and an 8% flip rate — but linear probing finds only 7 of 36 layers above chance (AUROC 0.541). The best behavioral fix uses the most diffuse internal mechanism.

Complete implementations of all major reinforcement learning algorithms from foundations to state-of-the-art.

Deep dive into SARSA, a foundational on-policy TD control algorithm for reinforcement learning.

Understanding the TD learning update rule and bootstrapping in reinforcement learning.

Guide to Monte Carlo methods in RL: learning from complete episodes and full returns.