Scitator
Scitator
Tl;dr
Posts
Talks
Publications
Projects
Contact
Light
Dark
Automatic
Sergey Kolesnikov
Latest
CORL: Research-oriented Deep Offline Reinforcement Learning Library
Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows
Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size
Towards Interaction-based User Embeddings in Sequential Recommender Models
EXACT: How to Train Your Accuracy
Showing your offline reinforcement learning work: Online evaluation budget matters
Deep Image Retrieval Is Not Robust To Label Noise
Prompts and Pre-Trained Language Models for Offline Reinforcement Learning
Probabilistic Embeddings Revisited
Showing your offline reinforcement learning work: Online evaluation budget matters
TTRS: Tinkoff Transactions Recommender System benchmark
Cite
×