Kutevedzera Kudzidza Quiz

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

1. Mukudzidza kwekutevedzera, mumiririri anowana sei maitiro ayo?
   • Kudzidza mutemo nekukopa zviratidzo zvenyanzvi
   • Kukwirisa mubairo wakagadzirwa nemaoko kuburikidza nekuongorora zvisina tsarukano
   • Kudzvanya neural network kumhanya pamidziyo midiki
   • Kugadzira mifananidzo kubva kumashoko ekurudziro
2. Behavioral cloning mafuremu ekutevedzera kudzidza serudzii rwedambudziko?
   • Kuungana kusingatarisirwi
   • Kutariswa kudzidza kwemamiriro-kune-chiito mepu
   • Chizvarwa chemhandu
   • Mubayiro kuumba
3. Idambudziko ripi rinokonzeresa kuti hunhu hwekuita cloning hukundikane pamusoro pekutevedzana kwechiito kwenguva refu?
   • Overfitting kune basa remubairo
   • Kunyangarika magradients mune encoder
   • Kukanganisa kukanganisa kubva pakuchinja kwekugovera
   • Njodzi kukanganwa makirasi ekare
4. Iyo DAgger algorithm inogadzirisa sei kushaya simba uku?
   • Nekubvisa nyanzvi kubva pachiuno zvachose
   • Nekuwedzera iyo discount factor
   • Nekuwedzera ruzha rusina kurongeka kune zvese zviito
   • Nekubvunza nyanzvi pamatunhu mudzidzi anoshanya nekuunganidza iyo data
5. Sei kudzidza kutevedzera kuchiwanzo kufarirwa pane kusimbisa kudzidza kwemabasa akaita sekutyaira?
   • Kuratidzira kuri nyore kupa pane basa remubairo rakarurama
   • Inovimbisa maitiro akanaka
   • Hazvimbodi chero data
   • Inomhanya nekukurumidza pakufungidzira chete
6. What is a realistic limitation of behavioral cloning when the agent reaches states outside the demonstrations?
   • It is guaranteed to improve beyond the expert
   • Its behavior is not guaranteed there because those states may be out of distribution
   • It can only produce random actions
   • It automatically queries an expert at every step
7. In one DAgger iteration, what does the learner do before requesting expert labels?
   • Deletes all earlier demonstrations
   • Trains only on randomly generated labels
   • Rolls out its current policy and records the states it actually visits
   • Replaces the expert policy permanently
8. After the expert labels the states visited by the current policy, what happens to that data?
   • It is used only as an evaluation metric
   • It replaces the original observation space
   • It is discarded after one gradient step
   • It is aggregated with previous labeled data for retraining