Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Ingham, Michel D."'
A large class of decision making under uncertainty problems can be described via Markov decision processes (MDPs) or partially observable MDPs (POMDPs), with application to artificial intelligence and operations research, among others. Traditionally,
Externí odkaz:
http://arxiv.org/abs/2109.04082
We consider the problem of designing policies for Markov decision processes (MDPs) with dynamic coherent risk objectives and constraints. We begin by formulating the problem in a Lagrangian framework. Under the assumption that the risk objectives and
Externí odkaz:
http://arxiv.org/abs/2012.02423
Technology development efforts in autonomy and cyber-defense have been evolving independently of each other, over the past decade. In this paper, we report our ongoing effort to integrate these two presently distinct areas into a single framework. To
Externí odkaz:
http://arxiv.org/abs/2002.01969
We consider the problem of designing policies for partially observable Markov decision processes (POMDPs) with dynamic coherent risk objectives. Synthesizing risk-averse optimal policies for POMDPs requires infinite memory and thus undecidable. To ov
Externí odkaz:
http://arxiv.org/abs/1909.12499
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Thesis (Sc. D.)--Massachusetts Institute of Technology, Dept. of Aeronautics and Astronautics, 2003.
Includes bibliographical references (p. 195-204).
There is growing demand for high-reliability embedded systems that operate robustly and a
Includes bibliographical references (p. 195-204).
There is growing demand for high-reliability embedded systems that operate robustly and a
Externí odkaz:
http://hdl.handle.net/1721.1/29745
Thesis (M.S.)--Massachusetts Institute of Technology, Dept. of Aeronautics and Astronautics, 1998.
Includes bibliographical references (p. 141-144).
by Michel D. Ingham.
M.S.
Includes bibliographical references (p. 141-144).
by Michel D. Ingham.
M.S.
Externí odkaz:
http://hdl.handle.net/1721.1/50384
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 35:11718-11725
We consider the problem of designing policies for Markov decision processes (MDPs) with dynamic coherent risk objectives and constraints. We begin by formulating the problem in a Lagrangian framework. Under the assumption that the risk objectives and
Publikováno v:
In Acta Astronautica 2006 58(12):648-661
Several distinct trends will influence space exploration missions in the next decade. Destinations are becoming more remote and mysterious, science questions more sophisticated, and, as mission experience accumulates, the most accessible targets are
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6e386d3a8d83da29a7bb2a2745074bc9