quiz bu lëkkale ak tegtal · Diggante Niveau

Q-Quiz jàng

Saytu Q-valeur yi, jàng ci bitti politik, yeesali Bellman, jàngat, xalaati daje ak li tax Q-jàngat amul benn model.

Yooni njiit yu jëm ciQ jàng
Laaj 1 de 8

Lu Q-valeur Q(s, a) di màndargaal?

Xoolaatal laaj bu nekk8 laaj

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

  1. Lu Q-valeur Q(s, a) di màndargaal?
    • Neexal bi ñuy seentu ci diir bu yàgg ci jël ay matuwaay ci etaa yi, ba noppi jëfandikoo ci anam wu gën
    • Probabilite nekk ci etaa s
    • Limu yoon yi ñu jéeme jëf a
    • Neexal bi ci saasi du jëf ludul
  2. Lan moo waral ñuy wax ni Q-Learning nekkul ci wàllu politik?
    • Dafay laaj xeetu environmaa bi
    • Mën na jàng politik bi gëna baax ci di topp beneen politik buy banneexu
    • Du dox ludul ci done yuñ denc
    • Dafay baña bàyyi xel ci neexal yi
  3. Ci sàrtu yeesal bi, lan la fakteer gamma biy wàññi?
    • Taux de exploration
    • Dayo tablo réew mi
    • Ñaata neexal lañuy xayma ci ëlëg suñu ko méngale ak yi ci saasi
    • Limu episod yi
  4. Lan moy njuumte ci diggante jamono (TD) ci Q-Learning?
    • wuute gi nekk ci digganté ñaari réew
    • Tolluwaayu neexal bi benn episod
    • Tolluwaayu jàng yoon gamma
    • r + gamma*max Q(s',a') dindi Q(s,a) bi fi nekk
  5. Lan moo waral Q-Learning bu tablo bu leer di xeex ak jafe-jafe yu mag yu melni jeu video yu bawoo ci pixel yi?
    • Limu etaa yi wuute dafa yaatu lool ngir ñu denc ko ci benn tablo
    • Mënul jëfandikoo neexal
    • Ñaari jëf kese lay dox
    • Gamma dafa wara tollu ci 1
  6. Lan mooy sabab tànneef jëf epsilon-greedy?
    • Tann jëf Q-value bi gëna mag saa yu nekk
    • ngir yemale banneexu jëf yu bees ak jëfandikoo jëf yu baax yiñ xam
    • Defar facteur de réduction
    • ngir denc tablo Q
  7. What exploration condition appears in the tabular Q-learning convergence result?
    • Only the greedy action is ever sampled
    • Each state must be visited exactly once
    • Every state-action pair must be visited repeatedly under suitable learning conditions
    • The transition model must be known in advance
  8. Why is Q-learning called model-free?
    • It never observes the environment
    • It does not use rewards
    • It requires a complete transition table before learning
    • It updates values from sampled rewards and next states without storing transition probabilities