Linear Programming and Sequential Decisions

By A. S. Manne. 1960

How researchers see this paper

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

Citations in the corpus

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…”
Min-max approximate dynamic programming (2011, methodology): “The condition we use to parameterize our family of bounds is related to the ‘linear programming approach’ to ADP, which was first introduced in [9], and extended to approximate dynamic programming in [10], [11].”
Approximate dynamic programming via iterated Bellman inequalities (2015, background): “The original characterization of the true value function via linear programming is due to Manne [Man60].”
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).”
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”
Restless Bandit Marginal Productivity Indices, Diminishing Returns, and Optimal Control of Make-to-Order/Make-to-Stock M/G/1 Queues (2006, background): “A deep connection between the mathematical programming and the dynamic programming approaches was revealed by D’Epénoux [11] and Manne [27], who showed that the optimality equations for a finite MDP can be formulated as a linear programming (LP) problem.”
The Simplex and Policy-Iteration Methods Are Strongly Polynomial for the Markov Decision Problem with a Fixed Discount Rate (2011, background): “Let P π ∈ I R m×m be the column stochastic matrix corresponding to a policy π, that is, the ith column of P π be the probability distribution p πi (i, i ), i = 1, · · · , m. * ≤ c π , ∀π, (2) where the ith entry of vector c π ∈ I R m equals the expected immediate cost i p πi (i, i )c πi (i, i ) for ”
Linear Programming for Large-Scale Markov Decision Problems (2014, unknown): “The MDP problem can also be stated in the LP formulation (Manne, 1960), s.t.”
Apprenticeship learning via inverse reinforcement learning (2004, background): “( Manne, 1960) Speci(cid:12)cally, in this LP the variables are the state/action visitation rates, and it is possible to place constraints on the learned policy’s stationary distribution directly.”
Efficient Sequential Decision Making (2017, methodology): “We can formulate the Bellman optimality equation as a linear program [36] by first noticing that if we have Lh ≥ h+ λ1 for some λ and h, we must have λ ≤ λ∗.”
On Linear Programming in a Markov Decision Problem (1970, methodology): “The model is analyzed by application, perhaps repeated, of a linear program first proposed by Manne [16] for a special case of this model.”