Tinkoff: Cracking AI ResearchLast updated on 27 Jan 2023 0 min read Go to Project Site2022Sergey KolesnikovHead of AI ResearchDecision Making in the WildPlease enable JavaScript to view the comments powered by Disqus.comments powered by DisqusRelatedTinkoff Pro Open SourceКак работает отдел исследований искусственного интеллекта в «Тинькофф»CORL: Research-oriented Deep Offline Reinforcement Learning LibraryLet Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing FlowsQ-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size