Black-box policy search with probabilistic programs
In this work we show how to represent policies as programs: that is, as stochastic simulators with tunable parameters. To learn the parameters of such policies we develop connections between black box variational inference and existing policy search approaches. We then explain how such learning can...
主要な著者: | Van De Meent, J, Paige, B, Tolpin, D, Wood, F |
---|---|
フォーマット: | Conference item |
出版事項: |
Journal of Machine Learning Research
2016
|
類似資料
-
Output-sensitive Adaptive Metropolis-Hastings for probabilistic programs
著者:: Tolpin, D, 等
出版事項: (2015) -
Maximum a posteriori estimation by search in probabilistic programs
著者:: Tolpin, D, 等
出版事項: (2015) -
Bayesian Optimization for Probabilistic Programs
著者:: Rainforth, T, 等
出版事項: (2016) -
Particle Gibbs with Ancestor Sampling for Probabilistic Programs
著者:: van de Meent, J, 等
出版事項: (2015) -
Particle Gibbs with ancestor sampling for probabilistic programs
著者:: Meent, J, 等
出版事項: (2015)