Reinforcement Learning
Learning systems that improve decisions through rewards, exploration, and sequential control. 3 topics in this category.
intermediate
Agent Reward Hacking
How autonomous AI agents exploit poorly secured evaluation infrastructure, and what zero-trust testing pipelines look like.
intermediateWhy you should care about PPO
why did ppo become the goat
intermediateQ-Learning
Model-free reinforcement learning algorithm that learns optimal action-value functions.