EasyDeepLearn

IQL — Implicit Q-Learning.

hard

Answer

  • Kostrikov et al. 2022.
  • Avoids explicit policy constraint or Q pessimism.
  • Uses expectile regression to approximate maxa\operatorname{max}_{a} Q(s, a) without evaluating Q at unseen actions — only uses actions from the data.
  • Extract policy via advantage-weighted regression on behavior policy.
  • Simpler, more stable than BCQ / CQL.
  • Often the modern default for offline RL benchmarks in 2023+.
Check yourself — multiple choice
  • Same as CQL
  • Expectile regression approximates maxa\operatorname{max}_{a} Q using only in-data actions (no OOD eval); extract policy via advantage-weighted regression on behavior; simpler + stable — 2023+ default
  • Random
  • Not real

IQL: expectile approx max; no OOD queries; AWR policy extraction; 2023+ default.

#offline-rl

Practise Reinforcement Learning

214 interview questions in this topic.

Related questions