2026
Evolutionary AI System for Scientific Discovery
Learnings
July 17, 2026
Agentic AI
Scientific Discovery
Genetic Algorithms
A review how evolutionary search can power AI systems for scientific discovery.
My Bizarre Adventure in RL: From PPO to GRPO
Learnings
June 28, 2026
Reinforcement Learning
Policy Gradient
Notes on the progression from policy gradients and PPO to GRPO for reinforcement learning.
My Bizarre Adventure in RL: Temporal-Difference Learning
Learnings
May 06, 2026
Reinforcement Learning
Stochastic Process
Markov Decision Process
Dynamic Programming
Monte Carlo Methods
A journey from Markov decision process to temporal-difference learning.
No matching posts
Try a different keyword or category.