Risk-Averse Decision Making Under Uncertainty: Difference between revisions
From Murray Wiki
Jump to navigationJump to search
(Created page with "{{Paper |Title=Risk-Averse Decision Making Under Uncertainty |Authors=Mohamadreza Ahmadi, Ugo Rosolia, Michel D. Ingham, Richard M. Murray, Aaron D. Ames |Source=AAAI Conference on Artificial Intelligence (AAAI-21) |Abstract=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...") |
No edit summary |
||
| Line 2: | Line 2: | ||
|Title=Risk-Averse Decision Making Under Uncertainty | |Title=Risk-Averse Decision Making Under Uncertainty | ||
|Authors=Mohamadreza Ahmadi, Ugo Rosolia, Michel D. Ingham, Richard M. Murray, Aaron D. Ames | |Authors=Mohamadreza Ahmadi, Ugo Rosolia, Michel D. Ingham, Richard M. Murray, Aaron D. Ames | ||
|Source=AAAI Conference on Artificial Intelligence (AAAI-21) | |Source=2021 AAAI Conference on Artificial Intelligence (AAAI-21) | ||
|Abstract=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 constraints can be represented by a Markov risk transition mapping, we propose an optimization-based method to synthesize Markovian policies that lower-bound the constrained risk-averse problem. We demonstrate that the formulated optimization problems are in the form of difference convex programs (DCPs) and can be solved by the disciplined convex-concave programming (DCCP) framework. We show that these results generalize linear programs for constrained MDPs with total discounted expected costs and constraints. Finally, we illustrate the effectiveness of the proposed method with numerical experiments on a rover navigatio | |Abstract=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 constraints can be represented by a Markov risk transition mapping, we propose an optimization-based method to synthesize Markovian policies that lower-bound the constrained risk-averse problem. We demonstrate that the formulated optimization problems are in the form of difference convex programs (DCPs) and can be solved by the disciplined convex-concave programming (DCCP) framework. We show that these results generalize linear programs for constrained MDPs with total discounted expected costs and constraints. Finally, we illustrate the effectiveness of the proposed method with numerical experiments on a rover navigatio | ||
|URL=https://arxiv.org/abs/2109.04082 | |URL=https://arxiv.org/abs/2109.04082 | ||
Latest revision as of 17:49, 9 October 2022
| Title | Risk-Averse Decision Making Under Uncertainty |
|---|---|
| Authors | Mohamadreza Ahmadi, Ugo Rosolia, Michel D. Ingham, Richard M. Murray and Aaron D. Ames |
| Source | 2021 AAAI Conference on Artificial Intelligence (AAAI-21) |
| Abstract | 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 constraints can be represented by a Markov risk transition mapping, we propose an optimization-based method to synthesize Markovian policies that lower-bound the constrained risk-averse problem. We demonstrate that the formulated optimization problems are in the form of difference convex programs (DCPs) and can be solved by the disciplined convex-concave programming (DCCP) framework. We show that these results generalize linear programs for constrained MDPs with total discounted expected costs and constraints. Finally, we illustrate the effectiveness of the proposed method with numerical experiments on a rover navigatio |
| Type | Conference paper |
| URL | https://arxiv.org/abs/2109.04082 |
| DOI | |
| Tag | Ahm+21-AAAI |
| ID | 2021n |
| Funding | AFOSR T&E |
| Flags |
