Denis Tarasov

7 papers · 2023–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11)

Venues

ICML (3) NeurIPS (3) AAAI (1)

Top co-authors

Alexander Nikulin (7) Vladislav Kurenkov (7) Sergey Kolesnikov (4) Ilya Zisman (3) Andrei Polubarov (3) Alexander Derevyagin (2) Lyubaykin Nikita (2) Igor Kiselev (2) Nikita Lyubaykin (1) Albina Klepach (1)

Research topics

Reinforcement Learning (7) Methods (6) Artificial Intelligence (3) Applications (3) Core AI (2) Learning Paradigms (2) Deep Learning (1) Machine Learning (1) Learning Types (1) Techniques (1)

Keywords

offline reinforcement learning (4) deep reinforcement learning (3) imitation learning (1) policy optimization (1) self-supervised learning (1) policy learning (1) value iteration (1) reward maximization (1) uncertainty estimation (1) latent action (1) soft actor-critic (1) actor-critic method (1) object-centric learning (1) downstream performance (1) linear probing (1) hyperparameter sensitivity (1) d4rl benchmark (1) feature-wise linear modulation (1) action model (1) random network distillation (1)

Papers

Object-Centric Latent Action Learning AAAI 2026 Latent Action Learning Requires Supervision in the Presence of Distractors ICML 2025 Vintix: Action Model via In-Context Reinforcement Learning ICML 2025 Anti-Exploration by Random Network Distillation ICML 2023 CORL: Research-oriented Deep Offline Reinforcement Learning Library NeurIPS 2023 Katakomba: Tools and Benchmarks for Data-Driven NetHack NeurIPS 2023 Revisiting the Minimalist Approach to Offline Reinforcement Learning NeurIPS 2023