philpaxReinforcement Learning
- Decisions & Dragons: A guide to the perilous world of reinforcement learning.
- Recent reasoning research: GRPO tweaks, base model RL, and data curation
- Towards Delivering a Coherent Self-Contained Explanation of Proximal Policy Optimization
- Applying RL: Fixing Structured Outputs
- The State of Reinforcement Learning for LLM Reasoning
- Reward Models
- Direct Preference Optimization (DPO)
- Reinforcement learning and general intelligence
- PPO for LLMs: A Guide for Normal People
- Group Relative Policy Optimization (GRPO)
- RL Scaling Laws
- Agentic RL
- Reinforcement Learning from Human Feedback Book