Sample Complexity and Overparameterization Bounds for Temporal-Difference Learning With Neural Network Approximation
Cayci, Semih (Corresponding author); Satpathi, Siddhartha; He, Niao; Srikant, R.
New York, NY : Institute of Electrical and Electronics Engineers (2023)
Journal Article
In: IEEE Transactions on Automatic Control
Volume: 68
Issue: 5
Page(s)/Article-Nr.: 2891-2905
Institutions
- Department of Mathematics [110000]
- Chair of Mathematics of Information Processing [114510]
- Junior Professor for Mathematics of Machine Learning [119730]
Identifier
- DOI: 10.1109/TAC.2023.3234234
- RWTH PUBLICATIONS: RWTH-2023-08433