Approximate Value Iteration for Risk-Aware Markov Decision Processes
From MaRDI portal
Abstract: We consider large-scale Markov decision processes (MDPs) with a risk measure of variability in cost, under the risk-aware MDPs paradigm. Previous studies showed that risk-aware MDPs, based on a minimax approach to handling risk, can be solved using dynamic programming for small to medium sized problems. However, due to the "curse of dimensionality", MDPs that model real-life problems are typically prohibitively large for such approaches. In this paper, we employ an approximate dynamic programming approach, and develop a family of simulation-based algorithms to approximately solve large-scale risk-aware MDPs. In parallel, we develop a unified convergence analysis technique to derive sample complexity bounds for this new family of algorithms.
Cited in
(9)- Approximate Value Iteration with Temporally Extended Actions
- On the relative value iteration with a risk-sensitive criterion
- Risk-averse learning by temporal difference methods with Markov risk measures
- Zeroth-order stochastic compositional algorithms for risk-aware learning
- Distributionally robust optimization for sequential decision-making
- The Value Iteration Algorithm in Risk-Sensitive Average Markov Decision Chains with Finite State Space
- Risk-averse dynamic programming for Markov decision processes
- Reinforcement learning with dynamic convex risk measures
- Error analysis for approximate CVaR-optimal control with a maximum cost
This page was built for publication: Approximate Value Iteration for Risk-Aware Markov Decision Processes
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4682381)
