Policy learning in continuous-time Markov decision processes using Gaussian Processes
Bartocci, Ezio; Bortolussi, Luca; Brázdil, Tomas; Milios, Dimitrios; Sanguinetti, Guido
- 期刊名称Performance Evaluation
- 作者Bartocci, Ezio; Bortolussi, Luca; Brázdil, Tomas; Milios, Dimitrios; Sanguinetti, Guido
- 印刷ISSN0166-5316
- 文件大小776.22KB
- 发表时间2017-9
- DOI10.1016/j.peva.2017.08.007