Upper Bounds for All and Max-gain Policy Iteration Algorithms on Deterministic MDPs
From MaRDI portal
Publication:6418767
arXiv2211.15602MaRDI QIDQ6418767
Pratyush Agarwal, Sushil Khyalia, Ritesh Goenka, Mulinti Shaik Wajid, Eashan Gupta, Shivaram Kalyanakrishnan
Publication date: 28 November 2022
Analysis of algorithms and problem complexity (68Q25) Extremal problems in graph theory (05C35) Paths and cycles (05C38) Markov and semi-Markov decision processes (90C40)
