Actor-only Deterministic Policy Gradient via Zeroth-order Gradient Oracles in Action Space

Harshat Kumar, Dionysios S. Kalogerias, George J. Pappas, Alejandro Ribeiro. Actor-only Deterministic Policy Gradient via Zeroth-order Gradient Oracles in Action Space. In IEEE International Symposium on Information Theory, ISIT 2021, Melbourne, Australia, July 12-20, 2021. pages 1676-1681, IEEE, 2021. [doi]

Abstract

Abstract is missing.