Controlled Markov decision processes with AVaR criteria for unbounded costs
From MaRDI portal
Publication:515747
DOI10.1016/j.cam.2016.11.052zbMath1358.90147arXiv1501.02518OpenAlexW2570125889MaRDI QIDQ515747
Publication date: 16 March 2017
Published in: Journal of Computational and Applied Mathematics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1501.02518
Related Items (6)
Effective Scenarios in Multistage Distributionally Robust Optimization with a Focus on Total Variation Distance ⋮ Zero-sum stochastic games with the average-value-at-risk criterion ⋮ Markov decision processes under model uncertainty ⋮ An average-value-at-risk criterion for Markov decision processes with unbounded costs ⋮ Minimizing spectral risk measures applied to Markov decision processes ⋮ Stochastic revision opportunities in Markov decision problems
Cites Work
- Unnamed Item
- Unnamed Item
- Weakly time consistent concave valuations and their dual representations
- Time-inconsistent multistage stochastic programs: martingale bounds
- Markov decision processes with applications to finance.
- On a time consistency concept in risk averse multistage stochastic programming
- Actuarial risk measures for financial derivative pricing
- On convex risk measures on \(L^{p}\)-spaces
- Extending pricing rules with general risk functions
- Optimal infinite-horizon feedback laws for a general class of constrained discrete-time systems: Stability and moving-horizon approximations
- Stochastic optimal control. The discrete time case
- Measurable selection theorems for optimization problems
- Optimal long term growth rate of expected utility of wealth
- Adaptive Markov control processes
- Dynamic consistency for stochastic optimal control problems
- Representation results for law invariant time consistent functions
- Markov decision processes with average-value-at-risk criteria
- Time consistency of dynamic risk measures
- The natural Banach space for version independent risk measures
- Coherent Measures of Risk
- Nonhomogeneous Markov Decision Processes with Borel State Space—The Average Criterion with Nonuniformly Bounded Rewards
- An existence theorem for discrete-time infinite-horizon optimal control problems
- Discounted MDP’s: Distribution Functions and Exponential Utility Maximization
- Control aspects of linear discrete time-varying systems
- Minimizing CVaR in global dynamic hedging with transaction costs
- Error bounds for rolling horizon policies in discrete-time Markov control processes
- Optimization of Convex Risk Functions
- On the Theory of Dynamic Programming
This page was built for publication: Controlled Markov decision processes with AVaR criteria for unbounded costs
