9 citations · 16 across the 18 of their papers we have counts for
18 papers
ReBRAC-v2: The Return of the King
Denis Tarasov, Robert K. Katzschmann
Recent offline reinforcement learning methods increasingly rely on expressive generative policies and specialized value-guidance mechanisms. We ask whether comparable progress can…
SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows
Chenyu Yang, Denis Tarasov, Davide Liconti +3
Real-world fine-tuning of dexterous manipulation policies remains challenging due to limited real-world interaction budgets and highly multimodal action distributions. Diffusion-ba…
Vision-Language Models Unlock Task-Centric Latent Actions
Alexander Nikulin, Ilya Zisman, Albina Klepach +5
Latent Action Models (LAMs) have rapidly gained traction as an important component in the pre-training pipelines of leading Vision-Language-Action models. However, they fail when o…
NinA: Normalizing Flows in Action. Training VLA Models with Normalizing Flows
Denis Tarasov, Alexander Nikulin, Ilya Zisman +5
Recent advances in Vision-Language-Action (VLA) models have established a two-component architecture, where a pre-trained Vision-Language Model (VLM) encodes visual observations an…
cadrille: Multi-modal CAD Reconstruction with Reinforcement Learning
Maksim Kolodiazhnyi, Denis Tarasov, Dmitrii Zhemchuzhnikov +6
Computer-Aided Design (CAD) plays a central role in engineering and manufacturing, making it possible to create precise and editable 3D models. Using a variety of sensor or user-pr…
Yes, Q-learning Helps Offline In-Context RL
Denis Tarasov, Alexander Nikulin, Ilya Zisman +6
Existing offline in-context reinforcement learning (ICRL) methods have predominantly relied on supervised training objectives, which are known to have limitations in offline RL set…
Object-Centric Latent Action Learning
Albina Klepach, Alexander Nikulin, Ilya Zisman +6
Leveraging vast amounts of unlabeled internet video data for embodied AI is currently bottlenecked by the lack of action labels and the presence of action-correlated visual distrac…
Latent Action Learning Requires Supervision in the Presence of Distractors
Alexander Nikulin, Ilya Zisman, Denis Tarasov +4
Recently, latent action learning, pioneered by Latent Action Policies (LAPO), have shown remarkable pre-training efficiency on observation-only data, offering potential for leverag…
Vintix: Action Model via In-Context Reinforcement Learning
Andrey Polubarov, Nikita Lyubaykin, Alexander Derevyagin +4
In-Context Reinforcement Learning (ICRL) represents a promising paradigm for developing generalist agents that learn at inference time through trial-and-error interactions, analogo…
The Role of Deep Learning Regularizations on Actors in Offline RL
Denis Tarasov, Anja Surina, Caglar Gulcehre
Deep learning regularization techniques, such as dropout, layer normalization, or weight decay, are widely adopted in the construction of modern artificial neural networks, often r…
Is Value Functions Estimation with Classification Plug-and-play for Offline Reinforcement Learning?
Denis Tarasov, Kirill Brilliantov, Dmitrii Kharlapenko
In deep Reinforcement Learning (RL), value functions are typically approximated using deep neural networks and trained via mean squared error regression objectives to fit the true…
Distilling LLMs' Decomposition Abilities into Compact Language Models
Denis Tarasov, Kumar Shridhar
Large Language Models (LLMs) have demonstrated proficiency in their reasoning abilities, yet their large size presents scalability challenges and limits any further customization.…
Katakomba: Tools and Benchmarks for Data-Driven NetHack
Vladislav Kurenkov, Alexander Nikulin, Denis Tarasov +1
NetHack is known as the frontier of reinforcement learning research where learning-based methods still need to catch up to rule-based solutions. One of the promising directions for…
Revisiting the Minimalist Approach to Offline Reinforcement Learning
Denis Tarasov, Vladislav Kurenkov, Alexander Nikulin +1
Recent years have witnessed significant advancements in offline reinforcement learning (RL), resulting in the development of numerous algorithms with varying degrees of complexity.…
Anti-Exploration by Random Network Distillation
Alexander Nikulin, Vladislav Kurenkov, Denis Tarasov +1
Despite the success of Random Network Distillation (RND) in various domains, it was shown as not discriminative enough to be used as an uncertainty estimator for penalizing out-of-…
Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows
Dmitriy Akimov, Vladislav Kurenkov, Alexander Nikulin +2
Offline reinforcement learning aims to train a policy on a pre-recorded and fixed dataset without any additional environment interactions. There are two major challenges in this se…
Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size
Alexander Nikulin, Vladislav Kurenkov, Denis Tarasov +2
Training large neural networks is known to be time-consuming, with the learning duration taking days or even weeks. To address this problem, large-batch optimization was introduced…
CORL: Research-oriented Deep Offline Reinforcement Learning Library
Denis Tarasov, Alexander Nikulin, Dmitry Akimov +2
CORL is an open-source library that provides thoroughly benchmarked single-file implementations of both deep offline and offline-to-online reinforcement learning algorithms. It emp…