In reinforcement learning, there are model-based versus model-free methods. Within model-based ones, there are policy-based and value-based methods.

AlphaGo Deepmind RL model has beaten the best Go human player. What kind of reinforcement model does it use? Why is this particular model appropriate for Go game?

  • $\begingroup$ I think their program is not just based on a single algorithm, and they used several algorithms in their design. However they have used deep reinforcement learning (There are several methods available, see for instance: "Human-level control through deep reinforcement learning"). The main difference between deep reinforcement learning and traditional Q- learning is that, tradition Q learning can only learn applicably when we have few states and actions say 10 or 20. $\endgroup$
    – Reza_va
    Commented Dec 24, 2020 at 1:25


You must log in to answer this question.