Home > Research > Publications & Outputs > Risk-Aware Stochastic Shortest Path
View graph of relations

Risk-Aware Stochastic Shortest Path

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Risk-Aware Stochastic Shortest Path. / Meggendorfer, Tobias.
AAAI-22 Technical Tracks 9. 2022. p. 9858-9867 (Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022; Vol. 36).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Meggendorfer, T 2022, Risk-Aware Stochastic Shortest Path. in AAAI-22 Technical Tracks 9. Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022, vol. 36, pp. 9858-9867. https://doi.org/10.1609/aaai.v36i9.21222

APA

Meggendorfer, T. (2022). Risk-Aware Stochastic Shortest Path. In AAAI-22 Technical Tracks 9 (pp. 9858-9867). (Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022; Vol. 36). https://doi.org/10.1609/aaai.v36i9.21222

Vancouver

Meggendorfer T. Risk-Aware Stochastic Shortest Path. In AAAI-22 Technical Tracks 9. 2022. p. 9858-9867. (Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022). doi: 10.1609/aaai.v36i9.21222

Author

Meggendorfer, Tobias. / Risk-Aware Stochastic Shortest Path. AAAI-22 Technical Tracks 9. 2022. pp. 9858-9867 (Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022).

Bibtex

@inproceedings{9645827b0456445491e19f9e0c02dfc6,
title = "Risk-Aware Stochastic Shortest Path",
abstract = "We treat the problem of risk-aware control for stochastic shortest path (SSP) on Markov decision processes (MDP). Typically, expectation is considered for SSP, which however is oblivious to the incurred risk. We present an alternative view, instead optimizing conditional value-at-risk (CVaR), an established risk measure. We treat both Markov chains as well as MDP and introduce, through novel insights, two algorithms, based on linear programming and value iteration, respectively. Both algorithms offer precise and provably correct solutions. Evaluation of our prototype implementation shows that riskaware control is feasible on several moderately sized models.",
author = "Tobias Meggendorfer",
year = "2022",
month = jun,
day = "28",
doi = "10.1609/aaai.v36i9.21222",
language = "English",
series = "Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022",
pages = "9858--9867",
booktitle = "AAAI-22 Technical Tracks 9",

}

RIS

TY - GEN

T1 - Risk-Aware Stochastic Shortest Path

AU - Meggendorfer, Tobias

PY - 2022/6/28

Y1 - 2022/6/28

N2 - We treat the problem of risk-aware control for stochastic shortest path (SSP) on Markov decision processes (MDP). Typically, expectation is considered for SSP, which however is oblivious to the incurred risk. We present an alternative view, instead optimizing conditional value-at-risk (CVaR), an established risk measure. We treat both Markov chains as well as MDP and introduce, through novel insights, two algorithms, based on linear programming and value iteration, respectively. Both algorithms offer precise and provably correct solutions. Evaluation of our prototype implementation shows that riskaware control is feasible on several moderately sized models.

AB - We treat the problem of risk-aware control for stochastic shortest path (SSP) on Markov decision processes (MDP). Typically, expectation is considered for SSP, which however is oblivious to the incurred risk. We present an alternative view, instead optimizing conditional value-at-risk (CVaR), an established risk measure. We treat both Markov chains as well as MDP and introduce, through novel insights, two algorithms, based on linear programming and value iteration, respectively. Both algorithms offer precise and provably correct solutions. Evaluation of our prototype implementation shows that riskaware control is feasible on several moderately sized models.

U2 - 10.1609/aaai.v36i9.21222

DO - 10.1609/aaai.v36i9.21222

M3 - Conference contribution/Paper

T3 - Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022

SP - 9858

EP - 9867

BT - AAAI-22 Technical Tracks 9

ER -