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...
Główni autorzy: | Van De Meent, J, Paige, B, Tolpin, D, Wood, F |
---|---|
Format: | Conference item |
Wydane: |
Journal of Machine Learning Research
2016
|
Podobne zapisy
-
Output-sensitive Adaptive Metropolis-Hastings for probabilistic programs
od: Tolpin, D, i wsp.
Wydane: (2015) -
Maximum a posteriori estimation by search in probabilistic programs
od: Tolpin, D, i wsp.
Wydane: (2015) -
Bayesian Optimization for Probabilistic Programs
od: Rainforth, T, i wsp.
Wydane: (2016) -
Particle Gibbs with Ancestor Sampling for Probabilistic Programs
od: van de Meent, J, i wsp.
Wydane: (2015) -
Particle Gibbs with ancestor sampling for probabilistic programs
od: Meent, J, i wsp.
Wydane: (2015)