TEXPLORE: real-time sample-efficient reinforcement learning for robots
نویسندگان
چکیده
منابع مشابه
Real-Time Interactive Reinforcement Learning for Robots
It is our goal to understand the role real-time human interaction can play in machine learning algorithms for robots. In this paper we present Interactive Reinforcement Learning (IRL) as a plausible approach for training human-centric assistive robots by natural interaction. We describe an experimental platform to study IRL, pose questions arising from IRL, and discuss initial observations obta...
متن کاملTEXPLORE: Temporal Difference Reinforcement Learning for Robots and Time-Constrained Domains
viii
متن کاملThe Open-Source TEXPLORE Code Release for Reinforcement Learning on Robots
The use of robots in society could be expanded by using reinforcement learning (RL) to allow robots to learn and adapt to new situations on-line. RL is a paradigm for learning sequential decision making tasks, usually formulated as a Markov Decision Process (MDP). For an RL algorithm to be practical for robotic control tasks, it must learn in very few samples, while continually taking actions i...
متن کاملMaking Reinforcement Learning Work on Real Robots
The Problem: Reinforcement-learning (RL) [1] techniques have elegant theoretical foundations and have proven useful in learning a variety of off-line tasks, such as playing Backgammon. However, they are still much too inefficient to be of use in the majority of robot-learning domains. In this project, we seek to make reinforcement learning effective for real robots. We are particularly interest...
متن کاملFuzzy Motion Control for Wheeled Mobile Robots in Real-Time
Due to various advantages of Wheeled Mobile Robots (WMRs), many researchers have focused to solve their challenges. The automatic motion control of such robots is an attractive problem and is one of the issues which should carefully be examined. In the current paper, the trajectory tracking problem of WMRs which are actuated by two independent electrical motors is deliberated. To this end, and ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Machine Learning
سال: 2012
ISSN: 0885-6125,1573-0565
DOI: 10.1007/s10994-012-5322-7