Monte Carlo Tree Search Quiz

Answers and explanations appear as you take the quiz.

1. What are the four main steps of a Monte Carlo Tree Search iteration?
   • Selection, Expansion, Simulation, Backpropagation
   • Sort, filter, merge, output
   • Encode, decode, attend, predict
   • Train, validate, test, deploy
2. What does the UCT selection formula balance?
   • Speed versus memory
   • Exploitation of high-value moves versus exploration of under-visited ones
   • Training versus inference
   • Width versus depth of the network
3. In classic MCTS, what happens during the 'simulation' (rollout) step?
   • The tree is deleted
   • The neural network is retrained
   • The game is played out to an outcome from the new node
   • All children are expanded at once
4. What roles did AlphaGo’s policy and value networks play in its MCTS search?
   • The policy network computed transitions and the value network chose the root child
   • Both networks performed random rollouts without evaluating positions
   • The value network proposed legal moves while the policy network estimated terminal rewards
   • The policy network guided move selection and the value network estimated position strength; AlphaGo also used a rollout policy
5. After many iterations, how does MCTS usually pick the final move to play?
   • The root child with the most visits
   • The move with the highest immediate reward
   • A random child
   • The deepest node in the tree
6. What makes MuZero notable compared to AlphaZero?
   • It uses no neural networks
   • It learns its own model of the environment, so it can plan without being given the rules
   • It only plays Go
   • It abandons tree search
7. In the UCT selection score, what does the exploration term reward?
   • Only the child with the highest raw reward
   • Moves that have already been selected most often, regardless of value
   • Children with fewer visits relative to their parent, encouraging further sampling
   • A random rollout’s final board size
8. Which MCTS iteration step adds a new child to the existing tree?
   • Selection
   • Simulation
   • Backpropagation
   • Expansion