AI engineering glossary · Reinforcement learning
What is alphaZero?
AlphaZero: A successor system that learns board games, including Go, chess and shogi, purely from self-play with no human game data, using a single network for both move probabilities and position value together with tree search.
AlphaZero: an example
Starting from random play with only the rules, it improves by playing itself and training on the results.
Related terms
More Reinforcement learning terms
- Baseline (policy gradient)
- Behavioural cloning
- Belief state
- Bellman backup
- Bellman equation
- Bellman optimality equation
- Bootstrapping
- Conservative Q-learning
Where you learn it
AlphaZero is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.