AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
RLHF — Reinforcement learning from human feedback — training a model to prefer answers humans rate as better, which turns a raw text predictor into a usable assistant.
fine-tuning — Taking a trained model and training it a bit more on your own examples so it gets better at one specific job.
Why it matters
A rigorous, foundational walkthrough of core RL algorithms (SARSA, Q-learning, policy gradients) that grounds the concepts increasingly relevant to AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → training and RLHFReinforcement learning from human feedback — training a model to prefer answers humans rate as better, which turns a raw text predictor into a usable assistant.Full definition →-style fine-tuningTaking a trained model and training it a bit more on your own examples so it gets better at one specific job.Full definition →, with clear explanations of how the methods actually differ.
Key quotes
“Very soon the extended algorithm AlphaGo Zero beat AlphaGo by 100-0 without supervised learning on human knowledge.”
Lilian Weng
“The goal of Reinforcement Learning (RL) is to learn a good strategy for the agent from experimental trials and relative simple feedback received. With the optimal strategy, the agent is capable to actively adapt to the environment to maximize future rewards.”
Lilian Weng
“TD learning is so important that Sutton & Barto (2017) in their RL book describes it as “one idea … central and novel to reinforcement learning”.”
Lilian Weng
“The key difference from SARSA is that Q-learning does not follow the current policy to pick the second action”
Lilian Weng
“Experience replay improves data efficiency, removes correlations in the observation sequences, and smooths over changes in the data distribution.”
