Q-Kudzidza Quiz

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

1. Ko Q-ukoshi Q(s, a) inomiririrei?
   • Mubairo unotarisirwa wenguva refu wekutora matanho a in state s, wobva waita nemazvo
   • Mukana wekuve muhurumende s
   • Nhamba yenguva chiito a chakaedzwa
   • Mubairo wepakarepo wekuita chete a
2. Sei Q-Kudzidza ichitsanangurwa se 'off-policy'?
   • Inoda muenzaniso wezvakatipoteredza
   • Inogona kudzidza iyo yakakwana mutemo uchitevera yakasiyana, yekuongorora mutemo
   • Inongoshanda pasina Indaneti pane data rakachengetwa
   • Inofuratira mibayiro zvachose
3. Mumutemo wekuvandudza, chii chinodzikisira chinhu gamma chinodzora?
   • Chiyero chekuongorora
   • Saizi yetafura yenyika
   • Yakawanda sei mibayiro yenguva yemberi inoyerwa kana ichienzaniswa neanokurumidza
   • Nhamba yezvikamu
4. Chii chinonzi temporal-difference (TD) kukanganisa muQ-Kudzidza?
   • Musiyano pakati penyika mbiri
   • Mubairo wakakwana wechikamu
   • Chiyero chekudzidza nguva gamma
   • r + gamma*max Q(s',a') kubvisa Q(s,a) fungidziro iripo
5. Sei yakajeka tabular Q-Kudzidza ichinetseka nematambudziko makuru semitambo yemavhidhiyo kubva kumapikisheni?
   • Huwandu hwematunhu akasiyana hwakakurisa zvekuti haugone kuchengetwa mutafura
   • Haikwanise kushandisa mibairo
   • Inoshanda chete nezviito zviviri
   • Gamma inofanira kuenzana ne1
6. Chii chinangwa che epsilon-kukara chiito sarudzo?
   • Kugara uchisarudza yepamusoro Q-kukosha chiito
   • Kuenzanisa kuongorora zviito zvitsva nekushandisa izvo zvinozivikanwa zvakanaka
   • Kuseta the discount factor
   • Kuchengeta Q-tafura
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