On Constraint Sampling in the Linear Programming Approach to Approximate Dynamic Programming
Published Online:1 Aug 2004https://doi.org/10.1287/moor.1040.0094
References
- Computational Learning Theory (1992) (Cambridge University Press, Cambridge, UK) 95Google Scholar
- Neuro-Dynamic Programming (1996) (Athena Scientific, Belmont, MA) Google Scholar
- Uncertain convex programs: Randomized solutions and confidence levels. (2003) . PreprintGoogle Scholar
- Las Vegas algorithms for linear and integer programming when the dimension is small. J. Assoc. Comput. Machinery (1995) 42(2):488–499Crossref, Google Scholar
- The linear programming approach to approximate dynamic programming. Oper. Res. (2003) 51(6):850–865Link, Google Scholar
- Central limit theorems for empirical measures. Ann. Probab. (1978) 6(6):899–929Crossref, Google Scholar
- Solution of large-scale symmetric travelling salesman problems. Math. Programming (1991) 51:141–202Crossref, Google Scholar
- Efficient solution algorithms for factored MDPs. J. Artificial Intelligence Res. (2003) 19:399–468Crossref, Google Scholar
- Equivalence of models for polynomial learnability. Inform. Comput. (1991) 95(2):129–161Crossref, Google Scholar
- New linear program performance bounds for queueing networks. J. Optim. Theory Appl. (1999) 100(3):575–597Crossref, Google Scholar
- Direct value-approximation for factored MDPs. Proc. 2001 Neural Inform. Processing Systems (NIPS) Conf., Adv. Neural Inform. Processing Systems (2002) 14(MIT Press, Cambridge, MA) Google Scholar
- Generalized polynomial approximations in Markovian decision processes. J. Math. Anal. Appl. (1985) 110:568–582Crossref, Google Scholar
- A linear programming approach to solving stochastic dynamic programs. (1993) . Unpublished manuscriptGoogle Scholar
- Spline approximations to value functions: A linear programming approach. Macroeconomic Dynam. (1997) 1:255–277Crossref, Google Scholar

