What question did this study set out to answer?

The aim is to introduce a linear programming method for solving Markov decision processes using approximate dynamic programming.

OR for the classroom: the linear programming approach to approximate dynamic programming for Markov decision processes

View Full Paper

Ask AI

Bookmark

Authors

Tutorial demonstrates linear programming techniques to solve Markov decision processes with high-dimensional states, suggesting practical solutions.

The aim is to introduce a linear programming method for solving Markov decision processes using approximate dynamic programming.
Presents three solution techniques: constraint sampling, constraint generation, and compact reformulation.
Focuses on infinite-horizon problems with a discounted-reward criterion.
Assumes audience familiarity with Markov decision processes, linear programming, and dynamic programming foundations.
Demonstrates the effectiveness of linear programming approaches in high-dimensional state spaces.
Utilizes a running example to clarify the methods and make key concepts more accessible.

Barz et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Tutorial demonstrates linear programming techniques to solve Markov decision processes with high-dimensional states, suggesting practical solutions.