An Expectation Maximization Algorithm for Continuous Markov Decision Processes with Arbitrary Reward

31 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.

A Distributional Perspective on Reinforcement Learning (2017, methodology): “The planning as inference approach (Toussaint & Storkey, 2006; Hoffman et al., 2009) embeds the return into a graphical model, and applies probabilistic inference to determine the sequence of actions leading to maximal expected reward.”
Perception, Action, and Utility: The Tangled Skein (2012, background): “A rich vein of recent work in machine learning has explored the idea that decision problems can be reframed as inference problems (Dayan and Hinton, 1997; Toussaint and Storkey, 2006; Hoffman et al., 2009; Vlassis and Toussaint, 2009; Theodorou et al., 2010).”
New inference strategies for solving Markov Decision Processes using reversible jump MCMC (2009, methodology): “For example, this strategy enabled (Hoﬀman et al., 2009) to relax the quadratic cost constraint in the classical and ubiquitous linear quadratic controllers via an EM algorithm with a tractable E step, but with general error functions.”
Bayesian Time Series Models: Expectation maximisation methods for solving (PO)MDPs and optimal control problems (2011, background): “generalize the EM algorithm for continuous MDPs ( Homan et al., 2009a ).”