We contribute Policy Reuse as a technique to improve a reinforcement learning agent with guidance from past learned similar policies. Our method relies on using the past policies ...
We describe a way of using multiple different types of similarity relationship to learn a low-dimensional embedding of a dataset. Our method chooses different, possibly overlappin...
Polymorphous computer-based systems are systems in which the CPU architecture “morphs” or changes shape to meet the requirements of the application. Optimized and efficient de...
Brandon Eames, Ted Bapty, Ben Abbott, Sandeep Neem...
System-on-a-chip (SOC) platform manufacturers are increasingly adding configurable features that provide power and performance flexibility in order to increase a platform's ap...
ESIGN. THE STEAM SIMULATOR LETS USERS ABSTRACT THE DETAILS OF LOW-LEVEL RECORDING PHYSICS AND HEAT TRANSFER PHENOMENA AND FACILITATES EXPLORATION OF A LARGE DESIGN SPACE OF STORAGE...
Sudhanva Gurumurthi, Youngjae Kim, Anand Sivasubra...