Learning Search Strategies from Human Demonstrations
Graph Chatbot
Chattez avec Graph Search
Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.
AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.
In this thesis, we study systems of linear and/or non-linear stochastic heat equations and fractional heat equations in spatial dimension 1 driven by space-time white noise. The main topic is the study of hitting probabilities for the solutions to these ...
Most policy search algorithms require thousands of training episodes to find an effective policy, which is often infeasible with a physical robot. This survey article focuses on the extreme other end of the spectrum: how can a robot adapt with only a handf ...
Several approaches have been proposed to assist humans in co-manipulation and teleoperation tasks given demonstrated trajectories. However, these approaches are not applicable when the demonstrations are suboptimal or when the generalization capabilities o ...
The majority of learning from demonstration approaches do not address suboptimal demonstrations or cases when drastic changes in the environment occur after the demonstrations were made. For example, in real teleoperation tasks, the demonstrations provided ...
Real-time video transcoding has recently raised as a valid alternative to address the ever-increasing demand for video contents in servers' infrastructures in current multi-user environments. High Efficiency Video Coding (HEVC) makes efficient online trans ...
A novel manifold learning approach is presented to incorporate computationally efficient obstacle avoidance constraints in optimal control algorithms. The method presented provides a significant computational benefit by reducing the number of constraints r ...
A long standing goal in artificial intelligence is to make robots seamlessly interact with humans in performing everyday manipulation skills. Learning from demonstrations or imitation learning provides a promising route to bridge this gap. In contrast to d ...
With the exponential growth of robotics and the fast development of their advanced cognitive and motor capabilities, one can start to envision humans and robots jointly working together in unstructured environments. Yet, for that to be possible, robots nee ...
The mechanical behavior of cellular matter in two dimensions can be inferred from geometric information near its energetic ground state. Here it is shown that the much larger set of all metastable state energies is universally described by a systematic exp ...
Generalizing manipulation skills to new situations requires extracting invariant patterns from demonstrations. For example, the robot needs to understand the demonstrations at a higher level while being invariant to the appearance of the objects, geometric ...
