
RiskAverse Decision Making Under Uncertainty
A large class of decision making under uncertainty problems can be descr...
read it

Verification of Markov Decision Processes with RiskSensitive Measures
We develop a method for computing policies in Markov decision processes ...
read it

Reinforcement Learning of RiskConstrained Policies in Markov Decision Processes
Markov decision processes (MDPs) are the defacto framework for sequenti...
read it

RiskAverse Stochastic Shortest Path Planning
We consider the stochastic shortest path planning problem in MDPs, i.e.,...
read it

Risksensitive Markov control processes
We introduce a general framework for measuring risk in the context of Ma...
read it

Conditional ValueatRisk for Reachability and Mean Payoff in Markov Decision Processes
We present the conditional valueatrisk (CVaR) in the context of Markov...
read it

RiskAverse Approximate Dynamic Programming with QuantileBased Risk Measures
In this paper, we consider a finitehorizon Markov decision process (MDP...
read it
Constrained RiskAverse Markov Decision Processes
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 optimizationbased method to synthesize Markovian policies that lowerbound the constrained riskaverse problem. We demonstrate that the formulated optimization problems are in the form of difference convex programs (DCPs) and can be solved by the disciplined convexconcave 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 navigation problem involving conditionalvalueatrisk (CVaR) and entropicvalueatrisk (EVaR) coherent risk measures.
READ FULL TEXT
Comments
There are no comments yet.