arXiv subjects

Aleksandr Panov

Publications and source records attributed to Aleksandr Panov.

At least 19 recordsLinked to original sources

arXiv2026

Causal Object-Centric Models for Planning with Monte Carlo Tree Search

We introduce COMET (Causal Object-centric Model for Efficient Tree search), a model-based reinforcement learning algorithm that performs Monte Carlo Tree Search in a slot-structured latent space. COMET pairs a frozen unsupervised object-centric encoder with a transformer-based world model, in which actions are bound to objects through a novel action-slot fusion mechanism that is used in slot transition prediction. Policy and value heads use object-causal attention, modulating token interactions by learned per-slot relevance scores so that decision-making concentrates on task-relevant entities. COMET adds an explicit object-level inductive bias to MuZero-style latent planning. Across eight visually and dynamically diverse tasks from the Object-Centric Visual RL benchmark, ManiSkill, Robosuite, and VizDoom, COMET achieves a higher mean normalized score during the early stages of training compared to object-centric and monolithic baselines.

cs.AI↗

arXiv2026

Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding

Multi-agent pathfinding (MAPF) is a widely used abstraction for multi-robot trajectory planning problems, where multiple homogeneous agents move simultaneously within a shared environment. Although solving MAPF optimally is NP-hard, scalable and efficient solvers are critical for real-world applications such as logistics and search-and-rescue. To this end, the research community has proposed various decentralized suboptimal MAPF solvers that leverage machine learning. Such methods frame MAPF (from a single agent perspective) as a Dec-POMDP where at each time step an agent has to decide an action based on the local observation and typically solve the problem via reinforcement learning or imitation learning. We follow the same approach but additionally introduce a learnable communication module tailored to enhance cooperation between agents via efficient feature sharing. We present the Local Communication for Multi-agent Pathfinding (LC-MAPF), a generalizable pre-trained model that applies multi-round communication between neighboring agents to exchange information and improve their coordination. Our experiments show that the introduced method outperforms the existing learning-based MAPF solvers, including IL and RL-based approaches, across diverse metrics in a diverse range of (unseen) test scenarios. Remarkably, the introduced communication mechanism does not compromise LC-MAPF's scalability, a common bottleneck for communication-based MAPF solvers.

cs.AI↗

arXiv2026

Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement Learning

We introduce SuperIgor, a framework for instruction-following tasks. Unlike prior methods that rely on predefined subtasks, SuperIgor enables a language model to generate and refine high-level plans through a self-learning mechanism, reducing the need for manual dataset annotation. Our approach involves iterative co-training: an RL agent is trained to follow the generated plans, while the language model adapts and modifies these plans based on RL feedback and preferences. This creates a feedback loop where both the agent and the planner improve jointly. We validate our framework in environments with rich dynamics and stochasticity. Results show that SuperIgor agents adhere to instructions more strictly than baseline methods, while also demonstrating strong generalization to previously unseen instructions.

cs.AI↗

arXiv2026

MARL-GPT: Foundation Model for Multi-Agent Reinforcement Learning

Recent advances in multi-agent reinforcement learning (MARL) have demonstrated success in numerous challenging domains and environments, but typically require specialized models for each task. In this work, we propose a coherent methodology that makes it possible for a single GPT-based model to learn and perform well across diverse MARL environments and tasks, including StarCraft Multi-Agent Challenge, Google Research Football and POGEMA. Our method, MARL-GPT, applies offline reinforcement learning to train at scale on the expert trajectories (400M for SMACv2, 100M for GRF, and 1B for POGEMA) combined with a single transformer-based observation encoder that requires no task-specific tuning. Experiments show that MARL-GPT achieves competitive performance compared to specialized baselines in all tested environments. Thus, our findings suggest that it is, indeed, possible to build a multi-task transformer-based model for a wide variety of (significantly different) multi-agent problems paving the way to the fundamental MARL model (akin to ChatGPT, Llama, Mistral etc. in natural language modeling).

cs.AI↗

arXiv2026

Knowledge-Guided Manipulation Using Multi-Task Reinforcement Learning

This paper introduces Knowledge Graph based Massively Multi-task Model-based Policy Optimization (KG-M3PO), a framework for multi-task robotic manipulation in partially observable settings that unifies Perception, Knowledge, and Policy. The method augments egocentric vision with an online 3D scene graph that grounds open-vocabulary detections into a metric, relational representation. A dynamic-relation mechanism updates spatial, containment, and affordance edges at every step, and a graph neural encoder is trained end-to-end through the RL objective so that relational features are shaped directly by control performance. Multiple observation modalities (visual, proprioceptive, linguistic, and graph-based) are encoded into a shared latent space, upon which the RL agent operates to drive the control loop. The policy conditions on lightweight graph queries alongside visual and proprioceptive inputs, yielding a compact, semantically informed state for decision making. Experiments on a suite of manipulation tasks with occlusions, distractors, and layout shifts demonstrate consistent gains over strong baselines: the knowledge-conditioned agent achieves higher success rates, improved sample efficiency, and stronger generalization to novel objects and unseen scene configurations. These results support the premise that structured, continuously maintained world knowledge is a powerful inductive bias for scalable, generalizable manipulation: when the knowledge module participates in the RL computation graph, relational representations align with control, enabling robust long-horizon behavior under partial observability.

cs.RO↗

arXiv2026

Revisiting Tree Search for LLMs: Gumbel and Sequential Halving for Budget-Scalable Reasoning

Neural tree search is a powerful decision-making algorithm widely used in complex domains such as game playing and model-based reinforcement learning. Recent work has applied AlphaZero-style tree search to enhance the reasoning capabilities of Large Language Models (LLMs) during inference, but we find that this approach suffers from a scaling failure: on GSM8K and Game24, accuracy drops as the search budget increases. In this paper, we present ReSCALE, an adaptation of Gumbel AlphaZero MCTS that replaces Dirichlet noise and PUCT selection with Gumbel sampling and Sequential Halving, restoring monotonic scaling without changes to the model or its training. ReSCALE reaches 58.4\% on GSM8K and 85.3\% on Game24 at budgets where the baseline degrades. Ablations confirm that Sequential Halving is the primary driver of the improvement.

cs.AI↗

arXiv2026

Object-Centric World Models Meet Monte Carlo Tree Search

In this paper, we introduce ObjectZero, a novel reinforcement learning (RL) algorithm that leverages the power of object-level representations to model dynamic environments more effectively. Unlike traditional approaches that process the world as a single undifferentiated input, our method employs Graph Neural Networks (GNNs) to capture intricate interactions among multiple objects. These objects, which can be manipulated and interact with each other, serve as the foundation for our model's understanding of the environment. We trained the algorithm in a complex setting teeming with diverse, interactive objects, demonstrating its ability to effectively learn and predict object dynamics. Our results highlight that a structured world model operating on object-centric representations can be successfully integrated into a model-based RL algorithm utilizing Monte Carlo Tree Search as a planning module.

cs.AI↗

arXiv2025

CoRL-MPPI: Enhancing MPPI With Learnable Behaviours For Efficient And Provably-Safe Multi-Robot Collision Avoidance

Decentralized collision avoidance is a core challenge for scalable multi-robot systems. A promising approach to this problem is Model Predictive Path Integral (MPPI) control - a framework that naturally handles arbitrary motion models and provides strong theoretical guarantees. Still, in practice an MPPI-based controller may produce suboptimal trajectories because its performance relies heavily on uninformed random sampling. We introduce CoRL-MPPI, a fusion of Cooperative Reinforcement Learning and MPPI that addresses this limitation. We train an action policy, approximated by a deep neural network, in simulation to learn local cooperative collision-avoidance behaviors. This learned policy is then embedded into the MPPI framework to guide its sampling distribution, biasing it toward more intelligent and cooperative actions in scenarios that may differ substantially from those used during training. Moreover, CoRL-MPPI preserves the theoretical guarantees of regular MPPI. We evaluate our approach in dense, dynamic setups against classical and learning-based state-of-the-art baselines. Our results demonstrate that CoRL-MPPI outperforms competing methods and significantly improves navigation efficiency, measured by success rate and delay, as well as safety, enabling agile and robust multi-robot navigation.

cs.RO↗

arXiv2025

CAMAR: Continuous Actions Multi-Agent Routing

Multi-agent reinforcement learning (MARL) is a powerful paradigm for solving cooperative and competitive decision-making problems. While many MARL benchmarks have been proposed, few combine continuous state and action spaces with challenging coordination and planning tasks. We introduce CAMAR, a new MARL benchmark designed explicitly for multi-agent pathfinding in environments with continuous actions. CAMAR supports cooperative and competitive interactions between agents and runs efficiently at up to 100,000 environment steps per second. We also propose a three-tier evaluation protocol to better track algorithmic progress and enable deeper analysis of performance. In addition, CAMAR allows the integration of classical planning methods such as RRT and RRT* into MARL pipelines. We use them as standalone baselines and combine RRT* with popular MARL algorithms to create hybrid approaches. We provide a suite of test scenarios and benchmarking tools to ensure reproducibility and fair comparison. Experiments show that CAMAR presents a challenging and realistic testbed for the MARL community.

cs.AI↗

arXiv2025

OVSegDT: Segmenting Transformer for Open-Vocabulary Object Goal Navigation

Open-vocabulary Object Goal Navigation requires an embodied agent to reach objects described by free-form language, including categories never seen during training. Existing end-to-end policies overfit small simulator datasets, achieving high success on training scenes but failing to generalize and exhibiting unsafe behaviour (frequent collisions). We introduce OVSegDT, a lightweight transformer policy that tackles these issues with two synergistic components. The first component is the semantic branch, which includes an encoder for the target binary mask and an auxiliary segmentation loss function, grounding the textual goal and providing precise spatial cues. The second component consists of a proposed Entropy-Adaptive Loss Modulation, a per-sample scheduler that continuously balances imitation and reinforcement signals according to the policy entropy, eliminating brittle manual phase switches. These additions cut the sample complexity of training by 33%, and reduce collision count in two times while keeping inference cost low (130M parameters, RGB-only input). On HM3D-OVON, our model matches the performance on unseen categories to that on seen ones and establishes state-of-the-art results (40.1% SR, 20.9% SPL on val unseen) without depth, odometry, or large vision-language models. Code is available at https://github.com/CognitiveAISystems/OVSegDT.

cs.RO↗

arXiv2025

Advancing Learnable Multi-Agent Pathfinding Solvers with Active Fine-Tuning

Multi-agent pathfinding (MAPF) is a common abstraction of multi-robot trajectory planning problems, where multiple homogeneous robots simultaneously move in the shared environment. While solving MAPF optimally has been proven to be NP-hard, scalable, and efficient, solvers are vital for real-world applications like logistics, search-and-rescue, etc. To this end, decentralized suboptimal MAPF solvers that leverage machine learning have come on stage. Building on the success of the recently introduced MAPF-GPT, a pure imitation learning solver, we introduce MAPF-GPT-DDG. This novel approach effectively fine-tunes the pre-trained MAPF model using centralized expert data. Leveraging a novel delta-data generation mechanism, MAPF-GPT-DDG accelerates training while significantly improving performance at test time. Our experiments demonstrate that MAPF-GPT-DDG surpasses all existing learning-based MAPF solvers, including the original MAPF-GPT, regarding solution quality across many testing scenarios. Remarkably, it can work with MAPF instances involving up to 1 million agents in a single environment, setting a new milestone for scalability in MAPF domains.

cs.AI↗

arXiv2025

M3PO: Massively Multi-Task Model-Based Policy Optimization

We introduce Massively Multi-Task Model-Based Policy Optimization (M3PO), a scalable model-based reinforcement learning (MBRL) framework designed to address sample inefficiency in single-task settings and poor generalization in multi-task domains. Existing model-based approaches like DreamerV3 rely on pixel-level generative models that neglect control-centric representations, while model-free methods such as PPO suffer from high sample complexity and weak exploration. M3PO integrates an implicit world model, trained to predict task outcomes without observation reconstruction, with a hybrid exploration strategy that combines model-based planning and model-free uncertainty-driven bonuses. This eliminates the bias-variance trade-off in prior methods by using discrepancies between model-based and model-free value estimates to guide exploration, while maintaining stable policy updates through a trust-region optimizer. M3PO provides an efficient and robust alternative to existing model-based policy optimization approaches and achieves state-of-the-art performance across multiple benchmarks.

cs.LG↗

arXiv2025

SGN-CIRL: Scene Graph-based Navigation with Curriculum, Imitation, and Reinforcement Learning

The 3D scene graph models spatial relationships between objects, enabling the agent to efficiently navigate in a partially observable environment and predict the location of the target object.This paper proposes an original framework named SGN-CIRL (3D Scene Graph-Based Reinforcement Learning Navigation) for mapless reinforcement learning-based robot navigation with learnable representation of open-vocabulary 3D scene graph. To accelerate and stabilize the training of reinforcement learning-based algorithms, the framework also employs imitation learning and curriculum learning. The first one enables the agent to learn from demonstrations, while the second one structures the training process by gradually increasing task complexity from simple to more advanced scenarios. Numerical experiments conducted in the Isaac Sim environment showed that using a 3D scene graph for reinforcement learning significantly increased the success rate in difficult navigation cases. The code is open-sourced and available at: https://github.com/Xisonik/Aloha\_graph.

cs.RO↗

arXiv2025

TOCALib: Optimal control library with interpolation for bimanual manipulation and obstacles avoidance

The paper presents a new approach for constructing a library of optimal trajectories for two robotic manipulators, Two-Arm Optimal Control and Avoidance Library (TOCALib). The optimisation takes into account kinodynamic and other constraints within the FROST framework. The novelty of the method lies in the consideration of collisions using the DCOL method, which allows obtaining symbolic expressions for assessing the presence of collisions and using them in gradient-based optimization control methods. The proposed approach allowed the implementation of complex bimanual manipulations. In this paper we used Mobile Aloha as an example of TOCALib application. The approach can be extended to other bimanual robots, as well as to gait control of bipedal robots. It can also be used to construct training data for machine learning tasks for manipulation.

cs.RO↗

arXiv2024

Dynamic Neural Potential Field: Online Trajectory Optimization in the Presence of Moving Obstacles

Generalist robot policies must operate safely and reliably in everyday human environments such as homes, offices, and warehouses, where people and objects move unpredictably. We present Dynamic Neural Potential Field (NPField-GPT), a learning-enhanced model predictive control (MPC) framework that couples classical optimization with a Transformer-based predictor of footprint-aware repulsive potentials. Given an occupancy sub-map, robot footprint, and optional dynamic-obstacle cues, our NPField-GPT model forecasts a horizon of differentiable potentials that are injected into a sequential quadratic MPC program via L4CasADi, yielding real-time, constraint-aware trajectory optimization. We additionally study two baselines: NPField-StaticMLP, where a dynamic scene is treated as a sequence of static maps; and NPField-DynamicMLP, which predicts the future potential sequence in parallel with an MLP. In dynamic indoor scenarios from BenchMR and on a Husky UGV in office corridors, NPField-GPT produces more efficient and safer trajectories under motion changes, while StaticMLP/DynamicMLP offer lower latency. We also compare with the CIAO* and MPPI baselines. Across methods, the Transformer+MPC synergy preserves the transparency and stability of model-based planning while learning only the part that benefits from data: spatiotemporal collision risk. Code and trained models are available at https://github.com/CognitiveAISystems/Dynamic-Neural-Potential-Field

cs.RO↗

arXiv2024

Maneuver Decision-Making with Trajectory Streams Prediction for Autonomous Vehicles

Decision-making, motion planning, and trajectory prediction are crucial in autonomous driving systems. By accurately forecasting the movements of other road users, the decision-making capabilities of the autonomous system can be enhanced, making it more effective in responding to dynamic and unpredictable environments and more adaptive to diverse road scenarios. This paper presents the FFStreams++ approach for decision-making and motion planning of different maneuvers, including unprotected left turn, overtaking, and keep-lane. FFStreams++ is a combination of sampling-based and search-based approaches, where iteratively new sampled trajectories for different maneuvers are generated and optimized, and afterward, a heuristic search planner is called, searching for an optimal plan. We model the autonomous diving system in the Planning Domain Definition Language (PDDL) and search for the optimal plan using a heuristic Fast-Forward planner. In this approach, the initial state of the problem is modified iteratively through streams, which will generate maneuver-specific trajectory candidates, increasing the iterating level until an optimal plan is found. FFStreams++ integrates a query-connected network model for predicting possible future trajectories for each surrounding obstacle along with their probabilities. The proposed approach was tested on the CommonRoad simulation framework. We use a collection of randomly generated driving scenarios for overtaking and unprotected left turns at intersections to evaluate the FFStreams++ planner. The test results confirmed that the proposed approach can effectively execute various maneuvers to ensure safety and reduce the risk of collisions with nearby traffic agents.

cs.RO↗

arXiv2024

MAPF-GPT: Imitation Learning for Multi-Agent Pathfinding at Scale

Multi-agent pathfinding (MAPF) is a problem that generally requires finding collision-free paths for multiple agents in a shared environment. Solving MAPF optimally, even under restrictive assumptions, is NP-hard, yet efficient solutions for this problem are critical for numerous applications, such as automated warehouses and transportation systems. Recently, learning-based approaches to MAPF have gained attention, particularly those leveraging deep reinforcement learning. Typically, such learning-based MAPF solvers are augmented with additional components like single-agent planning or communication. Orthogonally, in this work we rely solely on imitation learning that leverages a large dataset of expert MAPF solutions and transformer-based neural network to create a foundation model for MAPF called MAPF-GPT. The latter is capable of generating actions without additional heuristics or communication. MAPF-GPT demonstrates zero-shot learning abilities when solving the MAPF problems that are not present in the training dataset. We show that MAPF-GPT notably outperforms the current best-performing learnable MAPF solvers on a diverse range of problem instances and is computationally efficient during inference.

cs.MA↗

arXiv2024

Safe Policy Exploration Improvement via Subgoals

Reinforcement learning is a widely used approach to autonomous navigation, showing potential in various tasks and robotic setups. Still, it often struggles to reach distant goals when safety constraints are imposed (e.g., the wheeled robot is prohibited from moving close to the obstacles). One of the main reasons for poor performance in such setups, which is common in practice, is that the need to respect the safety constraints degrades the exploration capabilities of an RL agent. To this end, we introduce a novel learnable algorithm that is based on decomposing the initial problem into smaller sub-problems via intermediate goals, on the one hand, and respects the limit of the cumulative safety constraints, on the other hand -- SPEIS(Safe Policy Exploration Improvement via Subgoals). It comprises the two coupled policies trained end-to-end: subgoal and safe. The subgoal policy is trained to generate the subgoal based on the transitions from the buffer of the safe (main) policy that helps the safe policy to reach distant goals. Simultaneously, the safe policy maximizes its rewards while attempting not to violate the limit of the cumulative safety constraints, thus providing a certain level of safety. We evaluate SPEIS in a wide range of challenging (simulated) environments that involve different types of robots in two different environments: autonomous vehicles from the POLAMP environment and car, point, doggo, and sweep from the safety-gym environment. We demonstrate that our method consistently outperforms state-of-the-art competitors and can significantly reduce the collision rate while maintaining high success rates (higher by 80% compared to the best-performing methods).

cs.RO↗