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...
Autors principals: | Van De Meent, J, Paige, B, Tolpin, D, Wood, F |
---|---|
Format: | Conference item |
Publicat: |
Journal of Machine Learning Research
2016
|
Ítems similars
-
Output-sensitive Adaptive Metropolis-Hastings for probabilistic programs
per: Tolpin, D, et al.
Publicat: (2015) -
Maximum a posteriori estimation by search in probabilistic programs
per: Tolpin, D, et al.
Publicat: (2015) -
Bayesian Optimization for Probabilistic Programs
per: Rainforth, T, et al.
Publicat: (2016) -
Particle Gibbs with Ancestor Sampling for Probabilistic Programs
per: van de Meent, J, et al.
Publicat: (2015) -
Particle Gibbs with ancestor sampling for probabilistic programs
per: Meent, J, et al.
Publicat: (2015)