Ikibazo gihuza ibibazo · Hagati Urwego

Monte Carlo Igiti Gushakisha Ikibazo

Kugenzura ibyiciro bya MCTS, ubushakashatsi bwa UCT, kwigana kwigana, guhitamo imizi-uburyo uburyo AlphaGo yahujije gushakisha hamwe nurusobe.

Inzira zijyanye no kuyoboraGushakisha Igiti cya Monte Carlo
Ikibazo 1 Bya 8

Ni izihe ntambwe enye z'ingenzi zo gushakisha igiti cya Monte Carlo?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Ni izihe ntambwe enye z'ingenzi zo gushakisha igiti cya Monte Carlo?
    • Guhitamo, Kwaguka, Kwigana, Gusubira inyuma
    • Gutondeka, gushungura, guhuza, ibisohoka
    • Encode, decode, kwitabira, guhanura
    • Gutoza, kwemeza, kugerageza, kohereza
  2. Ni ubuhe buryo bwo guhitamo UCT buringaniza?
    • Umuvuduko nububiko
    • Gucukumbura-agaciro-kwimuka hamwe nubushakashatsi bwabasuwe
    • Amahugurwa nu mwanzuro
    • Ubugari n'uburebure bw'urusobe
  3. Muri MCTS ya kera, bigenda bite mugihe cya 'simulation' (rollout)?
    • Igiti cyasibwe
    • Urusobe rw'imitsi rwongeye gutozwa
    • Umukino ukinishwa ibisubizo bivuye kuri node nshya
    • Abana bose baragurwa icyarimwe
  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. Nyuma yo gusubiramo byinshi, nigute MCTS itora intambwe yanyuma yo gukina?
    • Umwana wumuzi ufite gusurwa cyane
    • Kwimuka hamwe nigihembo cyihuse
    • Umwana udasanzwe
    • Umuhengeri muremure mu giti
  6. Niki gituma MuZero igaragara cyane ugereranije na AlphaZero?
    • Ntabwo ikoresha imiyoboro
    • Yiga icyitegererezo cyayo cyibidukikije, bityo irashobora gutegura idahawe amategeko
    • Irakina Genda gusa
    • Ireka gushakisha ibiti
  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
    • Gusubira inyuma
    • Expansion