quiz bu lëkkale ak tegtal · Diggante Niveau

Quiz buy jàngale dooleel ay ndawu liggéey yu bari

Jàngaleel ni yenn ndawu jàngat yu am doole di jàngee ci biir neexal yu ñu bokk, soppi noon yi, xalaat yu xawa ñàkk ak ay jafe-jafe ci koordinaasioŋ.

Yooni njiit yu jëm ciJàngat buy dooleel Agent yu bari
Laaj 1 de 8

Lan moo tax environmaa bi 'dul taxaw' ci benn ndawu liggéey ci MARL?

Xoolaatal laaj bu nekk8 laaj

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

  1. Lan moo tax environmaa bi 'dul taxaw' ci benn ndawu liggéey ci MARL?
    • Yeneen ndawu liggéey yi ñu ngi jàng ak soppi seeni sàrt ci jamono jooju.
    • Fonksioŋu neexal bi dañu koy reset ci anam wu mucc episod bu nekk
    • Espace etat bi dafay màgg te amul àpp ci diir bi
    • Sensor yi deñuy delloosi seetlu yu bari
  2. Luy 'tàggat buñ dajale ak def lu jaxasoo' (CTDE)?
    • Agent yi dañu leen di tàggat, di doxal ci benn serwër bu mag
    • Benn ŋàññikat buñ bokk dafay jëfandikoo xibaar bu àdduna bi ci diiru tàggat yaram, waaye ndawu liggéey yi dañuy jëfandikoo seetlu yu bërëb bi ñuy dugal
    • Benn agent master mooy joxe ndigal ñeneen ñi yépp ci runtime
    • Done yiñ joxe ci tàggat yaram dañu leen boole waaye neexal yi dañu leen tàqale
  3. Ban kaadar math mooy yamale MDP bu benn ndawu liggéey ci ndawu liggéey yu bari?
    • Prograam bu ligneer
    • Benn xeetu Markov bu nëbbu
    • Jeu Markov (jeu stokastik)
    • Otomat bu am àpp
  4. Ci biir MARL bu amul benn lëkkaloo, naka lañuy jagleel neexal bi?
    • Agent bu nekk dafay yokk neexal bu baaxul ci beneen bi
    • Agent bi gëna gaaw kese mooy am neexal
    • Neexal yi ñu ngi leen di jox jéego bu nekk
    • Agent yi bokk nañu benn neexal bu ñu bokk
  5. Which training approach did OpenAI Five use to improve at Dota 2?
    • Self-play against copies of its own current and past policies
    • A fixed lookup table of human moves
    • A supervised-only classifier trained on image labels
    • A single policy trained only against a static scripted opponent
  6. Lan moo waral 'joxe leble' lu jafe la ci koperatiif MARL?
    • Neexal yi dañuy ñëw ci saasi te yomb nañu topp
    • Jafe na xam ban jëfi ndawu liggéey moo bokk ci njariñu ekip bi
    • Benn ndawu liggéey kese mooy am mbégte
    • Agent yi mënu ñu seetlu benn neexal
  7. What structural constraint does QMIX place on its mixing network?
    • It must be a linear sum with fixed weights
    • It ignores all individual agent values
    • The joint action-value is monotonic in each agent’s individual value
    • It requires communication at every action step
  8. How does Value Decomposition Networks (VDN) form the team action-value?
    • By multiplying all rewards by the number of agents
    • By selecting the largest local reward only
    • By training a separate team for each agent
    • By summing the individual agents’ action-values