Quiz buy jàngale doole ci net bi

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

1. Lan mooy jàngale dooleel ci net bi (batch)?
   • Jàng ci ab done bu takku te amul benn environmaa bu bees buy jaxasoo
   • Jàngale du lenn ludul jaare ci saytu ci saasi
   • Taggat yaram bu amul benn siñaal neexal
   • Dawal inference te amul benn model
2. Lan mooy jafe-jafe teknik bi gëna mag ci RL offline?
   • Ñàkum benn done
   • Coppite ci séddale ak xayma lu ëpp jëf yi nekk ci bitti séddale
   • Seetlu ci net bi lu ëpp
   • Parametre yu néew lool ci reso bi
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. naka lay def ba Q-Learning (CQL) di xeex lu ëpp luñuy xool?
   • Ni ñuy yokke valeur yi ci jëf yuñu gisul
   • Di dindi neexal bi yépp
   • Sooy gëna jàngat àdduna dëgg
   • Ni ñuy yamale Q-valeur yi ngir jëf yi nekk ci bitti séddale
5. naka lay def ba soppi dogal ci RL bi nekk ci biti?
   • Ni modelu toppalante buy wax luy waaja am ci jëf yi lalu ci delloo biñ bëgg
   • Ni mbooloo mu etaa yi
   • Seetug aleatër bu seer
   • Xeetu nataal buñ saytu
6. Lu tax algorithm RL yiñ miin ci net bi mënu ñu leen jëfandikoo ci anam wu yomb te nekkul ci net bi?
   • Amu ñu benn reso neuronal
   • Mënuñu dajale ay done yuy saafara jafe-jafe yi
   • Duñu musa jëfandikoo neexal
   • Duñu soxla benn politik
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