Ikibazo gihuza ibibazo · Hagati Urwego

Ikibazo Cyinshi cyo Gushimangira Kwiga Ikibazo

Wige uburyo abakozi benshi bashimangira-biga biga mubihembo bisangiwe, guhindura abatavuga rumwe, ibitekerezo byigice hamwe nimbogamizi.

Inzira zijyanye no kuyoboraKwiga Abakozi benshi
Ikibazo 1 Bya 8

Niki gituma ibidukikije 'bidahagarara' uhereye kumukozi umwe muri MARL?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Niki gituma ibidukikije 'bidahagarara' uhereye kumukozi umwe muri MARL?
    • Abandi bakozi icyarimwe biga kandi bagahindura politiki yabo
    • Igikorwa cyo guhemba gisubirwamo buri gice
    • Umwanya wa leta ukura nta mbibi zigihe
    • Sensors isubiza urusaku rwinshi
  2. Bisobanura iki 'amahugurwa yibanze hamwe no kwegereza ubuyobozi abaturage' (CTDE) bisobanura iki?
    • Abakozi batojwe kandi bakorera kuri seriveri imwe yo hagati
    • Abanenga basangiye bakoresha amakuru yisi yose mugihe cyamahugurwa, ariko abakozi bakora mubikorwa byo kwitegereza ahoherejwe
    • Umukozi umwe mukuru atanga amategeko kubandi bose mugihe cyo gukora
    • Amahugurwa yamakuru yibanze ariko ibihembo byegerejwe abaturage
  3. Ni ubuhe buryo bw'imibare bushyira hamwe umukozi umwe MDP kubakozi benshi?
    • Gahunda y'umurongo
    • Icyitegererezo cya Markov
    • Umukino wa Markov (umukino udasanzwe)
    • Imashini itagira ingano
  4. Mubufatanye bwa MARL gusa, ni gute ibihembo bisanzwe byubatswe?
    • Buri mukozi arenza igihembo aricyo kibi cyundi
    • Gusa umukozi wihuta yakira ibihembo byose
    • Ibihembo bitangwa uko bishakiye buri ntambwe
    • Abakozi basangiye ibihembo byikipe bahuriza hamwe
  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. Kuki 'kugenera inguzanyo' bigoye cyane muri koperative MARL?
    • Ibihembo bigera ako kanya kandi biroroshye kubikurikirana
    • Biragoye kumenya ibikorwa byumukozi byagize uruhare mubisubizo byitsinda
    • Hariho umukozi umwe gusa uhabwa ibihembo
    • Abakozi ntibashobora kubona ibihembo na gato
  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