14 citations · 52 across the 24 of their papers we have counts for
27 papers
Relational Object-Centric Actor-Critic
Leonid Ugadiarov, Vitaliy Vorobyov, Aleksandr I. Panov
The advances in unsupervised object-centric representation learning have significantly improved its application to downstream tasks. Recent works highlight that disentangled object…
Learning Successor Features with Distributed Hebbian Temporal Memory
Evgenii Dzhivelikian, Petr Kuderov, Aleksandr I. Panov
This paper presents a novel approach to address the challenge of online sequence learning for decision making under uncertainty in non-stationary, partially observable environments…
Evaluation of Safety Constraints in Autonomous Navigation with Deep Reinforcement Learning
Brian Angulo, Gregory Gorbov, Aleksandr Panov +1
While reinforcement learning algorithms have had great success in the field of autonomous navigation, they cannot be straightforwardly applied to the real autonomous systems withou…
Monte-Carlo Tree Search for Multi-Agent Pathfinding: Preliminary Results
Yelisey Pitanov, Alexey Skrynnik, Anton Andreychuk +2
In this work we study a well-known and challenging problem of Multi-agent Pathfinding, when a set of agents is confined to a graph, each agent is assigned a unique start and goal v…
Recurrent Action Transformer with Memory
Egor Cherepanov, Alexey Staroverov, Alexey K. Kovalev +1
Transformers have become increasingly popular in offline reinforcement learning (RL) due to their ability to treat agent trajectories as sequences, reframing policy learning as a s…
Intrinsic Motivation in Model-based Reinforcement Learning: A Brief Review
Artem Latyshev, Aleksandr I. Panov
The reinforcement learning research area contains a wide range of methods for solving the problems of intelligent agent control. Despite the progress that has been made, the task o…
Reinforcement Learning with Success Induced Task Prioritization
Maria Nesterova, Alexey Skrynnik, Aleksandr Panov
Many challenging reinforcement learning (RL) problems require designing a distribution of tasks that can be applied to train effective policies. This distribution of tasks can be s…
HPointLoc: Point-based Indoor Place Recognition using Synthetic RGB-D Images
Dmitry Yudin, Yaroslav Solomentsev, Ruslan Musaev +2
We present a novel dataset named as HPointLoc, specially designed for exploring capabilities of visual place recognition in indoor environment and loop detection in simultaneous lo…
Policy Optimization to Learn Adaptive Motion Primitives in Path Planning with Dynamic Obstacles
Brian Angulo, Aleksandr Panov, Konstantin Yakovlev
This paper addresses the kinodynamic motion planning for non-holonomic robots in dynamic environments with both static and dynamic obstacles -- a challenging problem that lacks a u…
TransPath: Learning Heuristics For Grid-Based Pathfinding via Transformers
Daniil Kirilenko, Anton Andreychuk, Aleksandr Panov +1
Heuristic search algorithms, e.g. A*, are the commonly used tools for pathfinding on grids, i.e. graphs of regular structure that are widely employed to represent environments in r…
Collecting Interactive Multi-modal Datasets for Grounded Language Understanding
Shrestha Mohanty, Negar Arabzadeh, Milagro Teruel +9
Human intelligence can remarkably adapt quickly to new tasks and environments. Starting from a very young age, humans acquire new skills and learn how to solve new tasks either by…
Learning to Solve Voxel Building Embodied Tasks from Pixels and Natural Language Instructions
Alexey Skrynnik, Zoya Volovikova, Marc-Alexandre Côté +9
The adoption of pre-trained language models to generate action plans for embodied agents is a promising research strategy. However, execution of instructions in real or simulated e…
POGEMA: Partially Observable Grid Environment for Multiple Agents
Alexey Skrynnik, Anton Andreychuk, Konstantin Yakovlev +1
We introduce POGEMA (https://github.com/AIRI-Institute/pogema) a sandbox for challenging partially observable multi-agent pathfinding (PO-MAPF) problems . This is a grid-based envi…
IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agents
Artem Zholus, Alexey Skrynnik, Shrestha Mohanty +5
We present the IGLU Gridworld: a reinforcement learning environment for building and evaluating language conditioned embodied agents in a scalable way. The environment features vis…
IGLU 2022: Interactive Grounded Language Understanding in a Collaborative Environment at NeurIPS 2022
Julia Kiseleva, Alexey Skrynnik, Artem Zholus +14
Human intelligence has the remarkable ability to adapt to new tasks and environments quickly. Starting from a very young age, humans acquire new skills and learn how to solve new t…
Interactive Grounded Language Understanding in a Collaborative Environment: IGLU 2021
Julia Kiseleva, Ziming Li, Mohammad Aliannejadi +18
Human intelligence has the remarkable ability to quickly adapt to new tasks and environments. Starting from a very young age, humans acquire new skills and learn how to solve new t…
Multitask Adaptation by Retrospective Exploration with Learned World Models
Artem Zholus, Aleksandr I. Panov
Model-based reinforcement learning (MBRL) allows solving complex tasks in a sample-efficient manner. However, no information is reused between the tasks. In this work, we propose a…
NeurIPS 2021 Competition IGLU: Interactive Grounded Language Understanding in a Collaborative Environment
Julia Kiseleva, Ziming Li, Mohammad Aliannejadi +12
Human intelligence has the remarkable ability to adapt to new tasks and environments quickly. Starting from a very young age, humans acquire new skills and learn how to solve new t…
Long-Term Exploration in Persistent MDPs
Leonid Ugadiarov, Alexey Skrynnik, Aleksandr I. Panov
Exploration is an essential part of reinforcement learning, which restricts the quality of learned policy. Hard-exploration environments are defined by huge state space and sparse…
Landmark Policy Optimization for Object Navigation Task
Aleksey Staroverov, Aleksandr I. Panov
This work studies object goal navigation task, which involves navigating to the closest object related to the given semantic category in unseen environments. Recent works have show…
Q-Mixing Network for Multi-Agent Pathfinding in Partially Observable Grid Environments
Vasilii Davydov, Alexey Skrynnik, Konstantin Yakovlev +1
In this paper, we consider the problem of multi-agent navigation in partially observable grid environments. This problem is challenging for centralized planning approaches as they,…
Delta Schema Network in Model-based Reinforcement Learning
Andrey Gorodetskiy, Alexandra Shlychkova, Aleksandr I. Panov
This work is devoted to unresolved problems of Artificial General Intelligence - the inefficiency of transfer learning. One of the mechanisms that are used to solve this problem in…
Forgetful Experience Replay in Hierarchical Reinforcement Learning from Demonstrations
Alexey Skrynnik, Aleksey Staroverov, Ermek Aitygulov +3
Currently, deep reinforcement learning (RL) shows impressive results in complex gaming and robotic environments. Often these results are achieved at the expense of huge computation…
Hierarchical Deep Q-Network from Imperfect Demonstrations in Minecraft
Alexey Skrynnik, Aleksey Staroverov, Ermek Aitygulov +3
We present Hierarchical Deep Q-Network (HDQfD) that took first place in the MineRL competition. HDQfD works on imperfect demonstrations and utilizes the hierarchical structure of e…