On Linear Programming in a Markov Decision Problem

How researchers see this paper

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

Reinforcement Learning via Fenchel-Rockafellar Duality (2020, background): “Although the LP perspective has existed for decades ( e.g. , Manne (1960); Denardo (1970)), it has recently received renewed interest for its potential ability to circumvent the optimization challenges of DP-based approaches in exchange for more mature and well-studied techniques associated with…”
The Linear Programming Approach to Approximate Dynamic Programming (2003, background): “Outline Markov decision processes Approximate Dynamic Programming Approximate linear programming Performance and Error Analysis Constraint Sampling http://www.mit.edu/∼pucci – p. 2/29”
Faster saddle-point optimization for solving large-scale Markov decision processes (2019, methodology): “…point is an alternative approach based on linear programming (LP), ﬁrst proposed roughly at the same time as the DP methods of Bellman (1957); Howard (1960): the idea of LP-based methods for sequential decision-making goes back to the works of de Ghellinck (1960); Manne (1960); Denardo (1970).”