2 papers
quant-ph2019
Deep Reinforcement Learning Control of Quantum Cartpoles
Zhikang T. Wang, Yuto Ashida, Masahito Ueda
We generalize a standard benchmark of reinforcement learning, the classical cartpole balancing problem, to the quantum regime by stabilizing a particle in an unstable potential thr…
cs.LG2019
Deep Gamblers: Learning to Abstain with Portfolio Theory
Liu Ziyin, Zhikang Wang, Paul Pu Liang +3
We deal with the \textit{selective classification} problem (supervised-learning problem with a rejection option), where we want to achieve the best performance at a certain level o…