Related papers: Q-attention: Enabling Efficient Learning for Visio…

Reinforcement learning (RL) algorithms have been around for decades and employed to solve various sequential decision-making problems. These algorithms however have faced great challenges when dealing with high-dimensional environments. The…

Automated industries lead to high quality production, lower manufacturing cost and better utilization of human resources. Robotic manipulator arms have major role in the automation process. However, for complex manipulation tasks, hard…

Mobile Manipulation (MM) systems are ideal candidates for taking up the role of a personal assistant in unstructured real-world environments. Among other challenges, MM requires effective coordination of the robot's embodiments for…

Sensor-based human activity recognition (HAR) requires to predict the action of a person based on sensor-generated time series data. HAR has attracted major interest in the past few years, thanks to the large number of applications enabled…

Model-based reinforcement learning (RL) has proven to be a data efficient approach for learning control tasks but is difficult to utilize in domains with complex observations such as images. In this paper, we present a method for learning…

To recognize an object in an image, the user must apply a combination of operators, where each operator has a set of parameters. These parameters must be well adjusted in order to reach good results. Usually, this adjustment is made…

Many real-world applications require an agent to make robust and deliberate decisions with multimodal information (e.g., robots with multi-sensory inputs). However, it is very challenging to train the agent via reinforcement learning (RL)…

Vision guided navigation requires processing complex visual information to inform task-orientated decisions. Applications include autonomous robots, self-driving cars, and assistive vision for humans. A key element is the extraction and…

Large sequence model (SM) such as GPT series and BERT has displayed outstanding performance and generalization capabilities on vision, language, and recently reinforcement learning tasks. A natural follow-up question is how to abstract…

Robot arms should be able to learn new tasks. One framework here is reinforcement learning, where the robot is given a reward function that encodes the task, and the robot autonomously learns actions to maximize its reward. Existing…

While contemporary reinforcement learning research and applications have embraced policy gradient methods as the panacea of solving learning problems, value-based methods can still be useful in many domains as long as we can wrangle with…

Adaptive Mesh Refinement (AMR) enhances the Finite Element Method, an important technique for simulating complex problems in engineering, by dynamically refining mesh regions, enabling a favorable trade-off between computational speed and…

We need to look at our shoelaces as we first learn to tie them but having mastered this skill, can do it from touch alone. We call this phenomenon "sensory scaffolding": observation streams that are not needed by a master might yet aid a…

This paper presents a novel approach to Multi-Agent Reinforcement Learning (MARL) that combines cooperative task decomposition with the learning of reward machines (RMs) encoding the structure of the sub-tasks. The proposed method helps…

Despite significant progress on multi-agent reinforcement learning (MARL) in recent years, coordination in complex domains remains a challenge. Work in MARL often focuses on solving tasks where agents interact with all other agents and…

Cooperative multi-agent reinforcement learning (MARL) has achieved significant results, most notably by leveraging the representation-learning abilities of deep neural networks. However, large centralized approaches quickly become…

We introduce a novel strategy for multi-robot sorting of waste objects using Reinforcement Learning. Our focus lies on finding optimal picking strategies that facilitate an effective coordination of a multi-robot system, subject to…

While the multi-branch architecture is one of the key ingredients to the success of computer vision tasks, it has not been well investigated in natural language processing, especially sequence learning tasks. In this work, we propose a…

When performing 3D manipulation tasks, robots have to execute action planning based on perceptions from multiple fixed cameras. The multi-camera setup introduces substantial redundancy and irrelevant information, which increases…

Reinforcement learning (RL) is a flexible and efficient method for programming micro-robots in complex environments. Here we investigate whether reinforcement learning can provide insights into biological systems when trained to perform…