Ikibazo gihuza ibibazo · Hagati Urwego

Offline Gukomeza Kwiga Ikibazo

Shakisha uburyo-bwibanze bwo gushimangira imyigire, gukwirakwiza, hamwe nuburyo bwo guhagararira ibintu hamwe nuburyo bukurikirana.

Inzira zijyanye no kuyoboraOffline Kwongera imbaraga
Ikibazo 1 Bya 8

Niki gisobanura kwiga kumurongo (batch) gushimangira?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Niki gisobanura kwiga kumurongo (batch) gushimangira?
    • Kwigira kuri dataset ihamye idafite ibidukikije bishya
    • Kwiga gusa binyuze mubushakashatsi burigihe
    • Amahugurwa nta kimenyetso cyerekana ibihembo
    • Gukoresha umwanzuro nta moderi iyo ari yo yose
  2. Ni ikihe kibazo nyamukuru cya tekiniki muri RL kumurongo?
    • Kubura amakuru ayo ari yo yose
    • Guhinduranya kugabura no gukabya ibikorwa-byo-gukwirakwiza ibikorwa
    • Ubushakashatsi bukabije kumurongo
    • Ibipimo bike cyane murusobe
  3. What does D4RL provide to researchers evaluating offline reinforcement-learning algorithms?
    • A guarantee that an offline policy is safe to deploy
    • A new optimizer that removes the need for logged data
    • A benchmark suite of datasets and tasks for offline RL evaluation
    • A dataset containing only online interactions collected by each test policy
  4. Nigute Conservative Q-Kwiga (CQL) irwanya gukabya?
    • Muguhindura indangagaciro kubikorwa bitagaragara
    • Mugukuraho ibihembo burundu
    • Mugushakisha byinshi mubyukuri
    • Muguhuza Q-indangagaciro hasi kubikorwa byo kugabura ibikorwa
  5. Nigute uhindura ibyemezo ahindura umurongo wa radiyo?
    • Nkurugero rwerekana urutonde rwibikorwa bisabwa kugaruka
    • Nka ihuriro ryibihugu
    • Nubushakashatsi butunguranye
    • Nkurwego rwo kugenzura amashusho
  6. Kuberiki bidashoboka kumurongo RL algorithms ikoreshwa gusa nkuko biri kumurongo?
    • Ntibafite urusobe rw'imitsi
    • Ntibashobora gukusanya amakuru akosora kugirango bakosore agaciro karenze
    • Ntibigera bakoresha ibihembo
    • Ntibasaba politiki
  7. How does BCQ reduce reliance on actions absent from an offline dataset?
    • It adds random actions to every training transition
    • It assumes every action has been observed equally often
    • It constrains candidate actions to stay near actions the dataset supports
    • It removes the action-value function and reward
  8. What value-learning method is central to the cited Implicit Q-Learning paper?
    • Maximum-likelihood fitting of a language tokenizer
    • Uniform regression over actions sampled from a live environment
    • A supervised image-classification loss
    • Expectile regression over values associated with dataset actions