Monte Carlo information-oriented planning

DOI10.3233/FAIA200368MaRDI QIDQ4999314zbMATH OpenFDO

Authors Vincent A. Thomas, Gérémy Hutin, Olivier Buffet

Publication date 6 July 2021

Full work available at URL https://arxiv.org/abs/2103.11345

Mathematics Subject Classification ID

Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Markov and semi-Markov decision processes (90C40)

Recommendations

• scientific article; zbMATH DE number 2243398
• Monte Carlo value iteration for continuous-state POMDPS
• POMDP solving: what rewards do you really expect at execution?
• Anytime point-based approximations for large POMDPS
• Point-based value iteration for continuous POMDPs

Cited in

(2)

• A further generalization of the finite-population Geiringer-like theorem for POMDPs to allow recombination overarbitrary set covers
• POMDP solving: what rewards do you really expect at execution?

This page was built for publication: Monte Carlo information-oriented planning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4999314)