相关论文: Experience Selection Using Dynamics Similarity for…

In this paper, we study the Tiered Reinforcement Learning setting, a parallel transfer learning framework, where the goal is to transfer knowledge from the low-tier (source) task to the high-tier (target) task to reduce the exploration risk…

When a robot learns from human examples, most approaches assume that the human partner provides examples of optimal behavior. However, there are applications in which the robot learns from non-expert humans. We argue that the robot should…

As human-robot collaboration is becoming more widespread, there is a need for a more natural way of communicating with the robot. This includes combining data from several modalities together with the context of the situation and background…

Transfer learning is a popular technique for improving the performance of neural networks. However, existing methods are limited to transferring parameters between networks with same architectures. We present a method for transferring…

Transferring knowledge from one neural network to another has been shown to be helpful for learning tasks with few training examples. Prevailing fine-tuning methods could potentially contaminate pre-trained features by comparably high…

In this paper we propose an algorithm for the training of neural network control policies for quadrotors. The learned control policy computes control commands directly from sensor inputs and is hence computationally efficient. An imitation…

Imitation learning, which enables robots to learn behaviors from demonstrations by human, has emerged as a promising solution for generating robot motions in such environments. The imitation learning-based robot motion generation method,…

Time perception is the phenomenological experience of time by an individual. In this paper, we study how to replicate neural mechanisms involved in time perception, allowing robots to take a step towards temporal cognition. Our framework…

Deep learning is known to be data-hungry, which hinders its application in many areas of science when datasets are small. Here, we propose to use transfer learning methods to migrate knowledge between different physical scenarios and…

Robots are required to autonomously respond to changing situations. Imitation learning is a promising candidate for achieving generalization performance, and extensive results have been demonstrated in object manipulation. However,…

Robot skills systems are meant to reduce robot setup time for new manufacturing tasks. Yet, for dexterous, contact-rich tasks, it is often difficult to find the right skill parameters. One strategy is to learn these parameters by allowing…

We study learning to learn for the multi-task structured bandit problem where the goal is to learn a near-optimal algorithm that minimizes cumulative regret. The tasks share a common structure and an algorithm should exploit the shared…

In order to be effective general purpose machines in real world environments, robots not only will need to adapt their existing manipulation skills to new circumstances, they will need to acquire entirely new skills on-the-fly. A great…

Transfer learning has become an essential paradigm in artificial intelligence, enabling the transfer of knowledge from a source task to improve performance on a target task. This approach, particularly through techniques such as pretraining…

Exploration is a fundamental problem in robotics. While sampling-based planners have shown high performance, they are oftentimes compute intensive and can exhibit high variance. To this end, we propose to directly learn the underlying…

Robots are used for collecting samples from natural environments to create models of, for example, temperature or algae fields in the ocean. Adaptive informative sampling is a proven technique for this kind of spatial field modeling. This…

Scene transfer for vision-based mobile robotics applications is a highly relevant and challenging problem. The utility of a robot greatly depends on its ability to perform a task in the real world, outside of a well-controlled lab…

Robotic manipulation can greatly benefit from the data efficiency, robustness, and predictability of model-based methods if robots can quickly generate models of novel objects they encounter. This is especially difficult when effects like…

Efficient learning from demonstration for long-horizon tasks remains an open challenge in robotics. While significant effort has been directed toward learning trajectories, a recent resurgence of object-centric approaches has demonstrated…

We have witnessed rapid evolution of deep neural network architecture design in the past years. These latest progresses greatly facilitate the developments in various areas such as computer vision and natural language processing. However,…