Reinforcement learning
Topics
- Meta learning
- Modeling animal behaviors with reinforcement learning
- Q learning
- Reinforcement learning from human feedback
Tutorials and lectures
- Reinforcement Learning: Machine Learning Meets Control Theory: a nice overview by Steven Brunton
- RL course by David Silver
- Reinforcement Learning: A Six Part Series by Mutual Information
- Demystifying Deep Reinforcement Learning
- How does DeepSeek learn? GRPO explained with Triangle Creatures - DeepSeek, GRPO
Books
Simple examples
vs. Evolution strategy
Evaluation
- Agarwal2021deep: uncertainty in evaluation is important. Deep RL tends to ignore and use only few runs to evaluate their performance.