Murray at 17:49, 9 October 2022

2022-10-09T17:49:09Z

← Older revision		Revision as of 17:49, 9 October 2022
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

Murray: 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..."

2022-10-09T17:07:05Z

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..."

New page

{{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 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
|Type=Conference paper
|ID=2021n
|Tag=Ahm+21-AAAI
|Funding=AFOSR T&E
}}

Risk-Averse Decision Making Under Uncertainty - Revision history

Murray at 17:49, 9 October 2022