The reward functions that drive reinforcement learning systems are generally derived directly from the descriptions of the problems that the systems are being used to solve. In so...
Reinforcement Learning is a commonly used technique in robotics, however, traditional algorithms are unable to handle large amounts of data coming from the robot’s sensors, requi...
— We propose a method that takes observations of a random vector as input, and learns to segment each observation into two disjoint parts. We show how to use the internal coheren...
Using the new wireless technologies, mobile devices with small displays (handhelds, PDAs, mobile phones) are present in many environments. We are interested in the effective use of...
It is widely accepted that the use of more compact representations than lookup tables is crucial to scaling reinforcement learning (RL) algorithms to real-world problems. Unfortun...
Satinder P. Singh, Tommi Jaakkola, Michael I. Jord...