no code implementations • 5 Feb 2020 • Kavosh Asadi, Neev Parikh, Ronald E. Parr, George D. Konidaris, Michael L. Littman
We show that the maximum action-value with respect to a deep RBVF can be approximated easily and accurately.
4 code implementations • 10 May 2019 • Craig J. Bester, Steven D. James, George D. Konidaris
Parameterised actions in reinforcement learning are composed of discrete actions with continuous action-parameters.
no code implementations • 12 Feb 2014 • Christopher Amato, George D. Konidaris, Gabriel Cruz, Christopher A. Maynor, Jonathan P. How, Leslie P. Kaelbling
We describe a probabilistic framework for synthesizing control policies for general multi-robot systems, given environment and sensor models and a cost function.