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, Manvel Avetisian, 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.
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.
This paper presents a novel approach to address the challenge of online hidden representation learning for decision-making under uncertainty in non-stationary, partially observable environments.
This paper proposes the Recurrent Memory Decision Transformer (RMDT), a model that uses a recurrent memory mechanism for reinforcement learning problems.
The reinforcement learning research area contains a wide range of methods for solving the problems of intelligent agent control.
To study the main stages of solving the place recognition problem on the HPointLoc dataset, we proposed a new modular approach named as PNTR.
We introduce POGEMA (https://github. com/AIRI-Institute/pogema) a sandbox for challenging partially observable multi-agent pathfinding (PO-MAPF) problems .
We present the IGLU Gridworld: a reinforcement learning environment for building and evaluating language conditioned embodied agents in a scalable way.
Model-based reinforcement learning (MBRL) allows solving complex tasks in a sample-efficient manner.
This work studies object goal navigation task, which involves navigating to the closest object related to the given semantic category in unseen environments.
In this paper, we consider the problem of multi-agent navigation in partially observable grid environments.
There are two main approaches to improving the sample efficiency of reinforcement learning methods - using hierarchical methods and expert demonstrations.
This work is devoted to unresolved problems of Artificial General Intelligence - the inefficiency of transfer learning.
We present Hierarchical Deep Q-Network (HDQfD) that took first place in the MineRL competition.
We introduce a new approach to hierarchy formation and task decomposition in hierarchical reinforcement learning.
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.