AIConfPaper
← Search

Alexander Nikulin

14 accepted papers

2026

Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learner

Andrei Polubarov, Lyubaykin Nikita, Alexander Derevyagin, Artyom Grishin, Igor Saprygin, Aleksandr Serkov +8
ICLR 2026poster

Recent progress in in-context reinforcement learning (ICRL) has demonstrated its potential for training generalist agents that can acquire new tasks directly at inference. Algorithm Distillation (AD) pioneered this paradigm and was subsequently scaled to multi-domain settings, although its ability t…

Cited by 0Source ↗Scholar ↗
2026

Object-Centric Latent Action Learning

Albina Klepach, Alexander Nikulin, Ilya Zisman, Denis Tarasov, Alexander Derevyagin, Andrei Polubarov +3
AAAI 2026technical

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 distractors. Although recent latent action policy optimization (LAPO) has shown promise in inferring proxy action labels from v

Cited by 0Source ↗PDF ↗Scholar ↗
2026

Zero-Shot Adaptation of Behavioral Foundation Models to Unseen Dynamics

Maksim Bobrin, Ilya Zisman, Alexander Nikulin, Vladislav Kurenkov, Dmitry V. Dylov
ICLR 2026poster

Behavioral Foundation Models (BFMs) proved successful in producing near-optimal policies for arbitrary tasks in a zero-shot manner, requiring no test-time retraining or task-specific fine-tuning. Among the most promising BFMs are the ones that estimate the successor measure learned in an unsupervise…

Cited by 0Source ↗code ↗Scholar ↗
2026

cadrille: Multi-modal CAD Reconstruction with Reinforcement Learning

Maksim Kolodiazhnyi, Denis Tarasov, Dmitrii Zhemchuzhnikov, Alexander Nikulin, Ilya Zisman, Anna Vorontsova +3
ICLR 2026oral

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-provided data as inputs for CAD reconstruction can democratize access to design applications. However, most existing metho…

Cited by 0Source ↗code ↗Scholar ↗
2025

Latent Action Learning Requires Supervision in the Presence of Distractors

Alexander Nikulin, Ilya Zisman, Denis Tarasov, Lyubaykin Nikita, Andrei Polubarov, Igor Kiselev +1
ICML 2025poster

Recently, latent action learning, pioneered by Latent Action Policies (LAPO), have shown remarkable pre-training efficiency on observation-only data, offering potential for leveraging vast amounts of video available on the web for embodied AI. However, prior work has focused on distractor-free data,…

Cited by 35Source ↗PDF ↗Scholar ↗
2025

Vintix: Action Model via In-Context Reinforcement Learning

Andrei Polubarov, Lyubaykin Nikita, Alexander Derevyagin, Ilya Zisman, Denis Tarasov, Alexander Nikulin +1
ICML 2025poster

In-Context Reinforcement Learning (ICRL) represents a promising paradigm for developing generalist agents that learn at inference time through trial-and-error interactions, analogous to how large language models adapt contextually, but with a focus on reward maximization. However, the scalability of…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2025

XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning

Alexander Nikulin, Ilya Zisman, Alexey Zemtsov, Vladislav Kurenkov
ICLR 2025poster

Following the success of the in-context learning paradigm in large-scale language and computer vision models, the recently emerging field of in-context reinforcement learning is experiencing a rapid growth. However, its development has been held back by the lack of challenging benchmarks, as all the…

Cited by 3Source ↗PDF ↗Scholar ↗
2024

Emergence of In-Context Reinforcement Learning from Noise Distillation

Ilya Zisman, Vladislav Kurenkov, Alexander Nikulin, Viacheslav Sinii, Sergey Kolesnikov
ICML 2024poster

Recently, extensive studies in Reinforcement Learning have been carried out on the ability of transformers to adapt in-context to various environments and tasks. Current in-context RL methods are limited by their strict requirements for data, which needs to be generated by RL agents or labeled with…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2024

In-Context Reinforcement Learning for Variable Action Spaces

Viacheslav Sinii, Alexander Nikulin, Vladislav Kurenkov, Ilya Zisman, Sergey Kolesnikov
ICML 2024poster

Recently, it has been shown that transformers pre-trained on diverse datasets with multi-episode contexts can generalize to new reinforcement learning tasks in-context. A key limitation of previously proposed models is their reliance on a predefined action space size and structure. The introduction…

Cited by 21Source ↗PDF ↗code ↗Scholar ↗
2024

XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX

Alexander Nikulin, Vladislav Kurenkov, Ilya Zisman, Artem Sergeevich Agarkov, Viacheslav Sinii, Sergey Kolesnikov
NeurIPS 2024poster

Inspired by the diversity and depth of XLand and the simplicity and minimalism of MiniGrid, we present XLand-MiniGrid, a suite of tools and grid-world environments for meta-reinforcement learning research. Written in JAX, XLand-MiniGrid is designed to be highly scalable and can potentially run on GP…

Cited by 23Source ↗PDF ↗code ↗Scholar ↗
2023

Anti-Exploration by Random Network Distillation

Alexander Nikulin, Vladislav Kurenkov, Denis Tarasov, Sergey Kolesnikov
ICML 2023poster

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-distribution actions in offline reinforcement learning. In this paper, we revisit these results and show that, with a na…

Cited by 40Source ↗PDF ↗code ↗Scholar ↗
2023

CORL: Research-oriented Deep Offline Reinforcement Learning Library

Denis Tarasov, Alexander Nikulin, Dmitry Akimov, Vladislav Kurenkov, Sergey Kolesnikov
NeurIPS 2023poster

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 emphasizes a simple developing experience with a straightforward codebase and a modern analysis tracking tool. In CORL, we…

Cited by 151Source ↗PDF ↗Scholar ↗
2023

Katakomba: Tools and Benchmarks for Data-Driven NetHack

Vladislav Kurenkov, Alexander Nikulin, Denis Tarasov, Sergey Kolesnikov
NeurIPS 2023poster

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 a breakthrough is using pre-collected datasets similar to recent developments in robotics, recommender systems, and mor…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2023

Revisiting the Minimalist Approach to Offline Reinforcement Learning

Denis Tarasov, Vladislav Kurenkov, Alexander Nikulin, Sergey Kolesnikov
NeurIPS 2023poster

Recent years have witnessed significant advancements in offline reinforcement learning (RL), resulting in the development of numerous algorithms with varying degrees of complexity. While these algorithms have led to noteworthy improvements, many incorporate seemingly minor design choices that impact…

Cited by 47Source ↗PDF ↗code ↗Scholar ↗