A Non-Parametric Approach to Dynamic Programming

20 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Modelling transition dynamics in MDPs with RKHS embeddings (2012, methodology): “The relatively poor scaling of NPDP with increased sample size is due to the numerical integration step in (Kroemer & Peters, 2011, Algorithm 1).”
Non-Parametric Approximate Linear Programming for MDPs (2011, methodology): “A more recent example is the work of Kroemer and Peters (2012) who also use kernel density estimates and Kveton and Theocharous (2012) who use cover trees to select a representative set of states.”
Non-parametric Policy Search with Limited Information Loss (2017, methodology): “…proposed for (partially observable) MDPs (Grünewälder et al., 2012b; Nishiyama et al., 2012), and non-parametric approximate dynamic programming method have been proposed by Ormoneit and Sen (2002), Taylor and Parr (2009), Deisenroth et al. (2009), Kroemer and Peters (2011) and Xu et al. (2014).”
Towards learning hierarchical skills for multi-phase manipulation tasks (2015, methodology): “We estimate the value function using non-parametric dynamic programming (NPDP) [23].”