Related papers: Self-supervised Learning of Image Embedding for Co…

Reinforcement learning (RL) methods have been shown to be capable of learning intelligent behavior in rich domains. However, this has largely been done in simulated domains without adequate focus on the process of building the simulator. In…

Improving sample efficiency is central to Reinforcement Learning (RL), especially in environments where the rewards are sparse. Some recent approaches have proposed to specify reward functions as manually designed or learned reward…

Reinforcement Learning (RL) methods have been proven successful in solving manipulation tasks autonomously. However, RL is still not widely adopted on real robotic systems because working with real hardware entails additional challenges,…

Learning actions that are relevant to decision-making and can be executed effectively is a key problem in autonomous robotics. Current state-of-the-art action representations in robotics lack proper effect-driven learning of the robot's…

We focus on developing efficient and reliable policy optimization strategies for robot learning with real-world data. In recent years, policy gradient methods have emerged as a promising paradigm for training control policies in simulation.…

This paper presents a novel state representation for reward-free Markov decision processes. The idea is to learn, in a self-supervised manner, an embedding space where distances between pairs of embedded states correspond to the minimum…

Classical policy search algorithms for robotics typically require performing extensive explorations, which are time-consuming and expensive to implement with real physical platforms. To facilitate the efficient learning of robot…

This paper discusses a system that accelerates reinforcement learning by using transfer from related tasks. Without such transfer, even if two tasks are very similar at some abstract level, an extensive re-learning effort is required. The…

Estimating the parameters of a model describing a set of observations using a neural network is in general solved in a supervised way. In cases when we do not have access to the model's true parameters this approach can not be applied.…

Quadruped robots have emerged as an evolving technology that currently leverages simulators to develop a robust controller capable of functioning in the real-world without the need for further training. However, since it is impossible to…

Self-training is a simple semi-supervised learning approach: Unlabelled examples that attract high-confidence predictions are labelled with their predictions and added to the training set, with this process being repeated multiple times.…

Traditional visual servoing methods suffer from serving between scenes from multiple perspectives, which humans can complete with visual signals alone. In this paper, we investigated how multi-perspective visual servoing could be solved…

Learning from Demonstrations (LfD) and Reinforcement Learning (RL) have enabled robot agents to accomplish complex tasks. Reward Machines (RMs) enhance RL's capability to train policies over extended time horizons by structuring high-level…

Self-supervised tasks such as colorization, inpainting and zigsaw puzzle have been utilized for visual representation learning for still images, when the number of labeled images is limited or absent at all. Recently, this worthwhile stream…

Deep learning techniques have been widely applied, achieving state-of-the-art results in various fields of study. This survey focuses on deep learning solutions that target learning control policies for robotics applications. We carry out…

Learned representations in deep reinforcement learning (DRL) have to extract task-relevant information from complex observations, balancing between robustness to distraction and informativeness to the policy. Such stable and rich…

Some of the threats in the dynamic environment include the unpredictability of the motion of objects and interferences to the robotic grasp. In such conditions the traditional supervised and reinforcement learning approaches are ill suited…

Recently it has been shown that precise dose control and an increase in the overall acquisition speed of atomic resolution scanning transmission electron microscope (STEM) images can be achieved by acquiring only a small fraction of the…

Many real-world control problems involve both discrete decision variables - such as the choice of control modes, gear switching or digital outputs - as well as continuous decision variables - such as velocity setpoints, control gains or…

A key challenge in scaling up robot learning to many skills and environments is removing the need for human supervision, so that robots can collect their own data and improve their own performance without being limited by the cost of…