no code implementations • 25 Dec 2024 • Alexandr Korchemnyi, Alexey K. Kovalev, Aleksandr I. Panov
In ArSyD, the object representation is obtained as a superposition of the generative factor vector representations.
no code implementations • 9 Dec 2024 • Egor Cherepanov, Nikita Kachaev, Artem Zholus, Alexey K. Kovalev, Aleksandr I. Panov
Using these definitions, we categorize different classes of agent memory, propose a robust experimental methodology for evaluating the memory capabilities of RL agents, and standardize evaluations.
1 code implementation • 12 Jul 2024 • Zoya Volovikova, Alexey Skrynnik, Petr Kuderov, Aleksandr I. Panov
In this study, we address the issue of enabling an artificial intelligence agent to execute complex language instructions within virtual environments.
1 code implementation • 8 Nov 2023 • Daniil Kirilenko, Vitaliy Vorobyov, Alexey K. Kovalev, Aleksandr I. Panov
Object-centric architectures usually apply a differentiable module to the entire feature map to decompose it into sets of entity representations called slots.
1 code implementation • 5 Nov 2023 • Artem Tsypin, Leonid Ugadiarov, Kuzma Khrabrov, Alexander Telepov, Egor Rumiantsev, Alexey Skrynnik, Aleksandr I. Panov, Dmitry Vetrov, Elena Tutubalina, Artur Kadurin
Our results demonstrate that the neural network trained with GOLF performs on par with the oracle on a benchmark of diverse drug-like molecules using $50$x less additional data.
no code implementations • 26 Oct 2023 • Leonid Ugadiarov, Aleksandr I. Panov
Our algorithm performs better in a visually complex 3D robotic environment and a 2D environment with compositional structure than the state-of-the-art model-free actor-critic algorithm built upon transformer architecture and the state-of-the-art monolithic model-based algorithm.
no code implementations • 20 Oct 2023 • Evgenii Dzhivelikian, Petr Kuderov, Aleksandr I. Panov
This paper presents a novel approach to address the challenge of online temporal memory learning for decision-making under uncertainty in non-stationary, partially observable environments.
1 code implementation • 15 Jun 2023 • Egor Cherepanov, Alexey Staroverov, Dmitry Yudin, Alexey K. Kovalev, Aleksandr I. Panov
We believe that our results will stimulate research on memory mechanisms for transformers applicable to offline reinforcement learning.
no code implementations • 24 Jan 2023 • Artem Latyshev, Aleksandr I. Panov
The reinforcement learning research area contains a wide range of methods for solving the problems of intelligent agent control.
Model-based Reinforcement Learning
reinforcement-learning
+2
1 code implementation • 30 Dec 2022 • Dmitry Yudin, Yaroslav Solomentsev, Ruslan Musaev, Aleksei Staroverov, Aleksandr I. Panov
To study the main stages of solving the place recognition problem on the HPointLoc dataset, we proposed a new modular approach named as PNTR.
1 code implementation • 22 Jun 2022 • Alexey Skrynnik, Anton Andreychuk, Konstantin Yakovlev, Aleksandr I. Panov
We introduce POGEMA (https://github. com/AIRI-Institute/pogema) a sandbox for challenging partially observable multi-agent pathfinding (PO-MAPF) problems .
1 code implementation • 31 May 2022 • Artem Zholus, Alexey Skrynnik, Shrestha Mohanty, Zoya Volovikova, Julia Kiseleva, Artur Szlam, Marc-Alexandre Coté, Aleksandr I. Panov
We present the IGLU Gridworld: a reinforcement learning environment for building and evaluating language conditioned embodied agents in a scalable way.
no code implementations • 25 Oct 2021 • Artem Zholus, Aleksandr I. Panov
Model-based reinforcement learning (MBRL) allows solving complex tasks in a sample-efficient manner.
1 code implementation • 21 Sep 2021 • Leonid Ugadiarov, Alexey Skrynnik, Aleksandr I. Panov
Exploration is an essential part of reinforcement learning, which restricts the quality of learned policy.
no code implementations • 17 Sep 2021 • 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.
1 code implementation • 13 Aug 2021 • Vasilii Davydov, Alexey Skrynnik, Konstantin Yakovlev, Aleksandr I. Panov
In this paper, we consider the problem of multi-agent navigation in partially observable grid environments.
1 code implementation • 17 Jun 2020 • Alexey Skrynnik, Aleksey Staroverov, Ermek Aitygulov, Kirill Aksenov, Vasilii Davydov, Aleksandr I. Panov
There are two main approaches to improving the sample efficiency of reinforcement learning methods - using hierarchical methods and expert demonstrations.
Deep Reinforcement Learning
Hierarchical Reinforcement Learning
+3
1 code implementation • 17 Jun 2020 • Andrey Gorodetskiy, Alexandra Shlychkova, Aleksandr I. Panov
This work is devoted to unresolved problems of Artificial General Intelligence - the inefficiency of transfer learning.
Model-based Reinforcement Learning
reinforcement-learning
+3
1 code implementation • 18 Dec 2019 • Alexey Skrynnik, Aleksey Staroverov, Ermek Aitygulov, Kirill Aksenov, Vasilii Davydov, Aleksandr I. Panov
We present Hierarchical Deep Q-Network (HDQfD) that took first place in the MineRL competition.
no code implementations • 13 Jun 2018 • Aleksandr I. Panov, Aleksey Skrynnik
We introduce a new approach to hierarchy formation and task decomposition in hierarchical reinforcement learning.
no code implementations • 27 Jul 2016 • Aleksandr I. Panov, Konstantin Yakovlev
On the subsymbolic level the task of path planning is considered and solved as a graph search problem.
no code implementations • 27 Jul 2016 • Aleksandr I. Panov, Konstantin Yakovlev
In this paper we outline the approach of solving special type of navigation tasks for robotic systems, when a coalition of robots (agents) acts in the 2D environment, which can be modified by the actions, and share the same goal location.