Reinforcement Learning
Reinforcement Learning
RL for LLMs, Part I: From REINFORCE to the Policy Gradient Theorem - Derive Everything Yourself
Read post →
Data Efficiency of RL Prediction Methods in Environments with Terminal-Only Rewards
Read post →
TD(0) & Q-Learning, as Robbins-Monro
Read post →
Batch TD(0) as Dynamic Programming on the Empirical MRP
Read post →