Turnpikes and Random Walk
Alexey Piunovskiy
TL;DR
This paper revises the theory of turnpikes in discounted Markov decision processes, proves a turnpike theorem for the undiscounted case, and applies these findings to the random walk model.
Contribution
It introduces new theoretical results for turnpikes in both discounted and undiscounted Markov decision processes, with applications to random walks.
Findings
Turnpike theorem proven for undiscounted Markov decision processes.
Revised theory of turnpikes in discounted models.
Application to random walk demonstrates practical relevance.
Abstract
In this paper we revise the theory of turnpikes in discounted Markov decision processes, prove the turnpike theorem for the undiscounted model and apply the results to the specific random walk.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsReinforcement Learning in Robotics · Formal Methods in Verification · Scheduling and Optimization Algorithms