Ilya Zisman

Alexander Nikulin, Vladislav Kurenkov, Ilya Zisman et al.

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 GPU or TPU accelerators, democratizing large-scale experimentation with limited resources. Along with the environments, XLand-MiniGrid provides pre-sampled benchmarks with millions of unique tasks of varying difficulty and easy-to-use baselines that allow users to quickly start training adaptive agents. In addition, we have conducted a preliminary analysis of scaling and generalization, showing that our baselines are capable of reaching millions of steps per second during training and validating that the proposed benchmarks are challenging. XLand-MiniGrid is open-source and available at https://github.com/dunnolab/xland-minigrid.

Viacheslav Sinii, Alexander Nikulin, Vladislav Kurenkov et al.

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 of a new action space often requires data re-collection and model re-training, which can be costly for some applications. In our work, we show that it is possible to mitigate this issue by proposing the Headless-AD model that, despite being trained only once, is capable of generalizing to discrete action spaces of variable size, semantic content and order. By experimenting with Bernoulli and contextual bandits, as well as a gridworld environment, we show that Headless-AD exhibits significant capability to generalize to action spaces it has never encountered, even outperforming specialized models trained for a specific set of actions on several environment configurations. Implementation is available at: https://github.com/corl-team/headless-ad.

Dmitry Ivanov, Ilya Zisman, Kirill Chernyshev

The majority of Multi-Agent Reinforcement Learning (MARL) literature equates the cooperation of self-interested agents in mixed environments to the problem of social welfare maximization, allowing agents to arbitrarily share rewards and private information. This results in agents that forgo their individual goals in favour of social good, which can potentially be exploited by selfish defectors. We argue that cooperation also requires agents' identities and boundaries to be respected by making sure that the emergent behaviour is an equilibrium, i.e., a convention that no agent can deviate from and receive higher individual payoffs. Inspired by advances in mechanism design, we propose to solve the problem of cooperation, defined as finding socially beneficial equilibrium, by using mediators. A mediator is a benevolent entity that may act on behalf of agents, but only for the agents that agree to it. We show how a mediator can be trained alongside agents with policy gradient to maximize social welfare subject to constraints that encourage agents to cooperate through the mediator. Our experiments in matrix and iterative games highlight the potential power of applying mediators in MARL.

Andrei Polubarov, Lyubaykin Nikita, Alexander Derevyagin et al.

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 to generalize to unseen tasks remained limited. The Decision Pre-Trained Transformer (DPT) was introduced as an alternative, showing stronger in-context reinforcement learning abilities in simplified domains, but its scalability had not been established. In this work, we extend DPT to diverse multi-domain environments, applying Flow Matching as a natural training choice that preserves its interpretation as Bayesian posterior sampling. As a result, we obtain an agent trained across hundreds of diverse tasks that achieves clear gains in generalization to the held-out test set. This agent improves upon prior AD scaling and demonstrates stronger performance in both online and offline inference, reinforcing ICRL as a viable alternative to expert distillation for training generalist agents.

Alexander Nikulin, Ilya Zisman, Albina Klepach et al.

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 observations contain action-correlated distractors, often encoding noise instead of meaningful latent actions. Humans, on the other hand, can effortlessly distinguish task-relevant motions from irrelevant details in any video given only a brief task description. In this work, we propose to utilize the common-sense reasoning abilities of Vision-Language Models (VLMs) to provide promptable representations, effectively separating controllable changes from the noise in unsupervised way. We use these representations as targets during LAM training and benchmark a wide variety of popular VLMs, revealing substantial variation in the quality of promptable representations as well as their robustness to different prompts and hyperparameters. Interestingly, we find that more recent VLMs may perform worse than older ones. Finally, we show that simply asking VLMs to ignore distractors can substantially improve latent action quality, yielding up to a six-fold increase in downstream success rates on Distracting MetaWorld.

Andrey Polubarov, Nikita Lyubaykin, Alexander Derevyagin et al.

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 ICRL beyond toy tasks and single-domain settings remains an open challenge. In this work, we present the first steps toward scaling ICRL by introducing a fixed, cross-domain model capable of learning behaviors through in-context reinforcement learning. Our results demonstrate that Algorithm Distillation, a framework designed to facilitate ICRL, offers a compelling and competitive alternative to expert distillation to construct versatile action models. These findings highlight the potential of ICRL as a scalable approach for generalist decision-making systems. Code released at https://github.com/dunnolab/vintix

Ilya Zisman, Vladislav Kurenkov, Alexander Nikulin et al.

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 actions from an optimal policy. In order to address this prevalent problem, we propose AD$^\varepsilon$, a new data acquisition approach that enables in-context Reinforcement Learning from noise-induced curriculum. We show that it is viable to construct a synthetic noise injection curriculum which helps to obtain learning histories. Moreover, we experimentally demonstrate that it is possible to alleviate the need for generation using optimal policies, with in-context RL still able to outperform the best suboptimal policy in a learning dataset by a 2x margin.

Denis Tarasov, Alexander Nikulin, Ilya Zisman et al.

Existing offline in-context reinforcement learning (ICRL) methods have predominantly relied on supervised training objectives, which are known to have limitations in offline RL settings. In this study, we explore the integration of RL objectives within an offline ICRL framework. Through experiments on more than 150 GridWorld and MuJoCo environment-derived datasets, we demonstrate that optimizing RL objectives directly improves performance by approximately 30% on average compared to widely adopted Algorithm Distillation (AD), across various dataset coverages, structures, expertise levels, and environmental complexities. Furthermore, in the challenging XLand-MiniGrid environment, RL objectives doubled the performance of AD. Our results also reveal that the addition of conservatism during value learning brings additional improvements in almost all settings tested. Our findings emphasize the importance of aligning ICRL learning objectives with the RL reward-maximization goal, and demonstrate that offline RL is a promising direction for advancing ICRL.

Alexander Nikulin, Ilya Zisman, Denis Tarasov et al.

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, where changes between observations are primarily explained by ground-truth actions. Unfortunately, real-world videos contain action-correlated distractors that may hinder latent action learning. Using Distracting Control Suite (DCS) we empirically investigate the effect of distractors on latent action learning and demonstrate that LAPO struggle in such scenario. We propose LAOM, a simple LAPO modification that improves the quality of latent actions by 8x, as measured by linear probing. Importantly, we show that providing supervision with ground-truth actions, as few as 2.5% of the full dataset, during latent action learning improves downstream performance by 4.2x on average. Our findings suggest that integrating supervision during Latent Action Models (LAM) training is critical in the presence of distractors, challenging the conventional pipeline of first learning LAM and only then decoding from latent to ground-truth actions.

Ilya Zisman, Alexander Nikulin, Viacheslav Sinii et al.

In-context learning allows models like transformers to adapt to new tasks from a few examples without updating their weights, a desirable trait for reinforcement learning (RL). However, existing in-context RL methods, such as Algorithm Distillation (AD), demand large, carefully curated datasets and can be unstable and costly to train due to the transient nature of in-context learning abilities. In this work, we integrated the n-gram induction heads into transformers for in-context RL. By incorporating these n-gram attention patterns, we considerably reduced the amount of data required for generalization and eased the training process by making models less sensitive to hyperparameters. Our approach matches, and in some cases surpasses, the performance of AD in both grid-world and pixel-based environments, suggesting that n-gram induction heads could improve the efficiency of in-context RL.

Denis Tarasov, Alexander Nikulin, Ilya Zisman et al.

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 and task descriptions, and an action decoder maps these representations to continuous actions. Diffusion models have been widely adopted as action decoders due to their ability to model complex, multimodal action distributions. However, they require multiple iterative denoising steps at inference time or downstream techniques to speed up sampling, limiting their practicality in real-world settings where high-frequency control is crucial. In this work, we present NinA (Normalizing Flows in Action), a fast and expressive alternative to diffusion-based decoders for VLAs. NinA replaces the diffusion action decoder with a Normalizing Flow (NF) that enables one-shot sampling through an invertible transformation, significantly reducing inference time. We integrate NinA into the FLOWER VLA architecture and fine-tune on the LIBERO benchmark. Our experiments show that NinA matches the performance of its diffusion-based counterpart under the same training regime, while achieving substantially faster inference. These results suggest that NinA offers a promising path toward efficient, high-frequency VLA control without compromising performance.

Maksim Bobrin, Ilya Zisman, Alexander Nikulin et al.

Behavioral Foundation Models (BFMs) proved successful in producing policies for arbitrary tasks in a zero-shot manner, requiring no test-time training or task-specific fine-tuning. Among the most promising BFMs are the ones that estimate the successor measure learned in an unsupervised way from task-agnostic offline data. However, these methods fail to react to changes in the dynamics, making them inefficient under partial observability or when the transition function changes. This hinders the applicability of BFMs in a real-world setting, e.g., in robotics, where the dynamics can unexpectedly change at test time. In this work, we demonstrate that Forward-Backward (FB) representation, one of the methods from the BFM family, cannot distinguish between distinct dynamics, leading to an interference among the latent directions, which parametrize different policies. To address this, we propose a FB model with a transformer-based belief estimator, which greatly facilitates zero-shot adaptation. We also show that partitioning the policy encoding space into dynamics-specific clusters, aligned with the context-embedding directions, yields additional gain in performance. These traits allow our method to respond to the dynamics observed during training and to generalize to unseen ones. Empirically, in the changing dynamics setting, our approach achieves up to a 2x higher zero-shot returns compared to the baselines for both discrete and continuous tasks.

Albina Klepach, Alexander Nikulin, Ilya Zisman et al.

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 visual observations, its performance degrades significantly when distractors are present. To address this limitation, we propose a novel object-centric latent action learning framework that centers on objects rather than pixels. We leverage self-supervised object-centric pretraining to disentangle action-related and distracting dynamics. This allows LAPO to focus on task-relevant interactions, resulting in more robust proxy-action labels, enabling better imitation learning and efficient adaptation of the agent with just a few action-labeled trajectories. We evaluated our method in eight visually complex tasks across the Distracting Control Suite (DCS) and Distracting MetaWorld (DMW). Our results show that object-centric pretraining mitigates the negative effects of distractors by 50%, as measured by downstream task performance: average return (DCS) and success rate (DMW).

Maksim Kolodiazhnyi, Denis Tarasov, Dmitrii Zhemchuzhnikov et al.

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, existing methods typically focus on a single input modality, such as point clouds, images, or text, which limits their generalizability and robustness. Leveraging recent advances in vision-language models (VLM), we propose a multi-modal CAD reconstruction model that simultaneously processes all three input modalities. Inspired by large language model (LLM) training paradigms, we adopt a two-stage pipeline: supervised fine-tuning (SFT) on large-scale procedurally generated data, followed by reinforcement learning (RL) fine-tuning using online feedback, obtained programatically. Furthermore, we are the first to explore RL fine-tuning of LLMs for CAD tasks demonstrating that online RL algorithms such as Group Relative Preference Optimization (GRPO) outperform offline alternatives. In the DeepCAD benchmark, our SFT model outperforms existing single-modal approaches in all three input modalities simultaneously. More importantly, after RL fine-tuning, cadrille sets new state-of-the-art on three challenging datasets, including a real-world one.

Alexander Nikulin, Ilya Zisman, Alexey Zemtsov et al.

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 experiments have been carried out in simple environments and on small-scale datasets. We present XLand-100B, a large-scale dataset for in-context reinforcement learning based on the XLand-MiniGrid environment, as a first step to alleviate this problem. It contains complete learning histories for nearly $30,000$ different tasks, covering $100$B transitions and 2.5B episodes. It took 50,000 GPU hours to collect the dataset, which is beyond the reach of most academic labs. Along with the dataset, we provide the utilities to reproduce or expand it even further. We also benchmark common in-context RL baselines and show that they struggle to generalize to novel and diverse tasks. With this substantial effort, we aim to democratize research in the rapidly growing field of in-context reinforcement learning and provide a solid foundation for further scaling.