AI engineering glossary · Reinforcement learning
What is alphaGo?
AlphaGo: A Go-playing system from DeepMind that combined deep neural networks for move choice and position evaluation with Monte Carlo tree search, trained first on human games and then by self-play. It defeated a top professional player in 2016.
AlphaGo: an example
Its policy network suggests likely moves and its value network judges positions, guiding the tree search.
Related terms
More Reinforcement learning terms
- AlphaZero
- Baseline (policy gradient)
- Behavioural cloning
- Belief state
- Bellman backup
- Bellman equation
- Bellman optimality equation
- Bootstrapping
Where you learn it
AlphaGo is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.