Robust approximate bilinear programming for value function approximation

MaRDI QIDQ5396717zbMATH OpenFDO

Authors Marek Petrik, Shlomo Zilberstein

Publication date 3 February 2014

Full work available at URL http://www.jmlr.org/papers/v12/petrik11a.html

zbMATH Keywords

approximate dynamic programmingMarkov decision processesvalue function approximation

Mathematics Subject Classification ID

Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Recommendations

• Dynamic programming and value-function approximation in sequential decision problems: error analysis and numerical results
• Continuous state dynamic programming via nonexpansive approximation
• The loss from imperfect value functions in exceptation-based and minimax-based tasks
• The loss from imperfect value functions in expectation-based and minimax-based tasks
• Approximate dynamic programming via iterated Bellman inequalities

Cited in

(7)

• The loss from imperfect value functions in exceptation-based and minimax-based tasks
• LP-based approximations for disjoint bilinear and two-stage adjustable robust optimization
• Multi-period price promotions in a single-supplier, multi-retailer supply chain under asymmetric demand information
• Solving dynamic public insurance games with endogenous agent distributions: theory and computational approximation
• Learning heuristic functions for large state spaces
• Degeneracy removal in cutting plane methods for disjoint bilinear programming
• The loss from imperfect value functions in expectation-based and minimax-based tasks

This page was built for publication: Robust approximate bilinear programming for value function approximation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5396717)