ConceptAI & ML
Monte Carlo tree search
A search algorithm used in decision-making processes, particularly in games, that builds a search tree by simulating random playouts.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Search tree3Game theory1Markov decision processes1Monte-Carlo control1Monte-Carlo evaluation1Planning algorithms1Policy1Reinforcement learning1
Opens up
Concepts that name this one as a prerequisite.
Lecturers
4Each in their own terms, from the easiest level.
Sergey Levine
A planning method that considers closed-loop feedback and is commonly used for discrete states and board games.Sasha Rush
A search algorithm combining search with exploration by walking down a tree to a leaf node, expanding next steps, running rollouts, and updating parent nodes.David Silver
An algorithm that builds a search tree using simulated trajectories and evaluates state-action pairs by mean returns to improve the simulation policy.
Lectures that assume it
1Connections
13The lectures that define it or assume it, and the concepts next to it.
Concepts8
- Search tree
- Game theory
- Markov decision processes
- Default policy
- Smooth UCT
- Temporal-difference search (TD search)