Accelerated modified policy iteration algorithms for Markov decision processes
From MaRDI portal
Publication:2391867
Abstract: One of the most widely used methods for solving average cost MDP problems is the value iteration method. This method, however, is often computationally impractical and restricted in size of solvable MDP problems. We propose acceleration operators that improve the performance of the value iteration for average reward MDP models. These operators are based on two important properties of Markovian operator: contraction mapping and monotonicity. It is well known that the classical relative value iteration methods for average cost criteria MDP do not involve the max-norm contraction or monotonicity property. To overcome this difficulty we propose to combine acceleration operators with variants of value iteration for stochastic shortest path problems associated average reward problems.
Recommendations
- Acceleration Operators in the Value Iteration Algorithms for Markov Decision Processes
- Multiply accelerated value iteration for nonsymmetric affine fixed point problems and application to Markov decision processes
- Monotone value iteration for discounted finite Markov decision processes
- Generic rank-one corrections for value iteration in Markovian decision problems
- A K-step look-ahead analysis of value iteration algorithms for Markov decision processes
Cites work
- scientific article; zbMATH DE number 18886 (Why is no real title available?)
- scientific article; zbMATH DE number 700091 (Why is no real title available?)
- scientific article; zbMATH DE number 1953446 (Why is no real title available?)
- A K-step look-ahead analysis of value iteration algorithms for Markov decision processes
- A modified dynamic programming method for Markovian decision problems
- Accelerating Procedures of the Value Iteration Algorithm for Discounted Markov Decision Processes, Based on a One-Step Lookahead Analysis
- Acceleration Operators in the Value Iteration Algorithms for Markov Decision Processes
- Algorithms for Stochastic Games with Geometrical Interpretation
- Generic rank-one corrections for value iteration in Markovian decision problems
- Modified Policy Iteration Algorithms for Discounted Markov Decision Problems
- Technical Note—Accelerated Computation of the Expected Discounted Return in a Markov Chain
- The Linear Programming Approach to Approximate Dynamic Programming
- Value iteration and optimization of multiclass queueing networks
Cited in
(13)- Truncated policy iteration methods
- Multiply accelerated value iteration for nonsymmetric affine fixed point problems and application to Markov decision processes
- Acceleration Operators in the Value Iteration Algorithms for Markov Decision Processes
- A First-Order Approach to Accelerated Value Iteration
- scientific article; zbMATH DE number 6542806 (Why is no real title available?)
- Policy iteration type algorithms for recurrent state Markov decision processes
- Generic rank-one corrections for value iteration in Markovian decision problems
- Interval iteration algorithm for MDPs and IMDPs
- An Accelerated Value/Policy Iteration Scheme for Optimal Control Problems and Games
- Policy iteration accelerated with Krylov methods
- Accelerating the convergence of value iteration by using partial transition functions
- Prioritization methods for accelerating MDP solvers
- On iterative optimization ol structured Markov decision processes with discounted rewards
This page was built for publication: Accelerated modified policy iteration algorithms for Markov decision processes
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2391867)
