Welcome
Hi, welcome!
Posts
- RL for LLMs, Part I: From REINFORCE to the Policy Gradient Theorem - Derive Everything Yourself
- Data Efficiency of RL Prediction Methods in Environments with Terminal-Only Rewards
- TD(0) & Q-Learning, as Robbins-Monro
- Batch TD(0) as Dynamic Programming on the Empirical MRP
- ML Environment Engineering: Building Machines That Build Machines
- Agents: From Inference-Time Scaffolding to Inference-Time Compute