As soon as the robots step out in the real and uncertain world, they have to adapt to various unanticipated situations by acquiring new skills as quickly as possible. Unfortunately, on robots, current state-of-the-art reinforcement learning (e.g., deep-reinforcement learning) algorithms require large interaction time to train a new skill. In this thesis, we have explored methods to allow a robot to acquire new skills through trial-and-error within a few minutes of physical interaction. Our primary focus is to incorporate prior knowledge from a simulator with real-world experiences of a robot to achieve rapid learning and adaptation. In our first contribution, we propose a novel model-based policy search algorithm called Multi-DEX that (1) i...
Most policy search algorithms require thousands of training episodes to find an effective policy, wh...
In the past few years, deep reinforcement learning (RL) has shown great potential in learning action...
This article describes a proposal to achieve fast robot learning from its interaction with the envir...
Quand les robots doivent affronter le monde réel, ils doivent s'adapter à diverses situations imprév...
International audienceMeta-learning algorithms can accelerate the model-based reinforcement learning...
Video: http://tiny.cc/aprol_videoInternational audienceRepertoire-based learning is a data-efficient...
Les robots opèrent dans le monde réel, dans lequel essayer quelque chose prend beaucoup de temps. ...
Robots have transformed many industries, most notably manufacturing, and have the power to deliver t...
The main objective of this thesis is to propose a new method for online adaptation of robotic learni...
International audienceMost policy search (PS) algorithms require thousands of training episodes to f...
The context of this work is the emergence of service Robotics, where robots will need adaptive capab...
In this work, we study how the notion of behavioral habit, inspired from the study of biology, can b...
Recently, vision and learning made significant progress that could improve robot control policies fo...
In this article we describe a novel algorithm that allows fast and continuous learning on a physical...
In machine learning, meta-learning methods aim for fast adaptability to unknown tasks using prior kn...
Most policy search algorithms require thousands of training episodes to find an effective policy, wh...
In the past few years, deep reinforcement learning (RL) has shown great potential in learning action...
This article describes a proposal to achieve fast robot learning from its interaction with the envir...
Quand les robots doivent affronter le monde réel, ils doivent s'adapter à diverses situations imprév...
International audienceMeta-learning algorithms can accelerate the model-based reinforcement learning...
Video: http://tiny.cc/aprol_videoInternational audienceRepertoire-based learning is a data-efficient...
Les robots opèrent dans le monde réel, dans lequel essayer quelque chose prend beaucoup de temps. ...
Robots have transformed many industries, most notably manufacturing, and have the power to deliver t...
The main objective of this thesis is to propose a new method for online adaptation of robotic learni...
International audienceMost policy search (PS) algorithms require thousands of training episodes to f...
The context of this work is the emergence of service Robotics, where robots will need adaptive capab...
In this work, we study how the notion of behavioral habit, inspired from the study of biology, can b...
Recently, vision and learning made significant progress that could improve robot control policies fo...
In this article we describe a novel algorithm that allows fast and continuous learning on a physical...
In machine learning, meta-learning methods aim for fast adaptability to unknown tasks using prior kn...
Most policy search algorithms require thousands of training episodes to find an effective policy, wh...
In the past few years, deep reinforcement learning (RL) has shown great potential in learning action...
This article describes a proposal to achieve fast robot learning from its interaction with the envir...