Variance Reduction Methods for Sublinear Reinforcement Learning
Sham Kakade, Mengdi Wang, Lin F. Yang
TL;DR
This paper intended to analyze variance reduction techniques in sublinear reinforcement learning but was withdrawn due to an unfixable technical issue in the analysis.
Contribution
The paper aimed to contribute new variance reduction methods for sublinear reinforcement learning but was withdrawn before publication.
Findings
No experimental results due to withdrawal
Technical analysis was incomplete
Paper was withdrawn before final conclusions
Abstract
There is a technical issue in the analysis that is not easily fixable. We, therefore, withdraw the submission. Sorry for the inconvenience.
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 · Advanced Control Systems Optimization · Control Systems and Identification
MethodsQ-Learning