2 papers
cs.LG2018
Kickstarting Deep Reinforcement Learning
Simon Schmitt, Jonathan J. Hudson, Augustin Zidek +8
We present a method for using previously-trained 'teacher' agents to kickstart the training of a new 'student' agent. To this end, we leverage ideas from policy distillation and po…
physics.data-an2015
An algorithm for discovering Lagrangians automatically from data
D. J. A. Hills, A. M. Grütter, J. J. Hudson
An activity fundamental to science is building mathematical models. These models are used to both predict the results of future experiments and gain insight into the structure of t…