// ♞ Reinforcement Learning
Q-Learning
Learns the long-term value of each action in each state.
Q 学习 1992 Foundational core
IN PLAIN WORDS
Repeatedly update Q toward reward plus discounted best next-state Q (Bellman). Model-free and off-policy, it founds value-based RL.
Used in: Game AI, recommendation, control
TIMELINE · prerequisites → this → what builds on it
01Original paper
Q-learning
Watkins et al. · Machine Learning · 1992
DOI ↗ ✓ Verified · Crossref API doi:10.1007/BF00992698
02Where it sits
Learn the left column first; the right column builds on this one.
Learn first
Q-Learning
Then you can learn
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
04Where the course teaches it
For AI / data
- Verification: verified, checked 2026-10-21.
- JSON: /api/learn/algorithms.json (id:
q-learning)