2 papers
cs.LG2020
An exact solution in Markov decision process with multiplicative rewards as a general framework
Yuan Yao, Xiaolin Sun
We develop an exactly solvable framework of Markov decision process with a finite horizon, and continuous state and action spaces. We first review the exact solution of conventiona…
cond-mat.mtrl-sci2019
Leveraging Legacy Data to Accelerate Materials Design via Preference Learning
Xiaolin Sun, Zhufeng Hou, Masato Sumita +3
Machine learning applications in materials science are often hampered by shortage of experimental data. Integration with legacy data from past experiments is a viable way to solve…