The use of reinforcement learning for robot teams has enabled complex tasks to be performed, but at the cost of requiring a large amount of exploration. Exchanging information …
S Daniluk, R Emami - International Journal of Robotics and …, 2020 - diva-portal.org
This paper presents an advice mechanism compatible with heterogeneous advisers that incorporates advice into the advisee's policy via a method guaranteeing convergence to an …
S Daniluk - Ph. D. Thesis, 2017 - ui.adsabs.harvard.edu
The use of reinforcement learning for robot teams has enabled complex tasks to be performed, but at the cost of requiring a large amount of exploration. Exchanging information …
An Advice Mechanism for Heterogeneous Robot Teams by Steven Daniluk A thesis submitted in conformity with the requirements for t Page 1 An Advice Mechanism for Heterogeneous Robot …
The use of reinforcement learning for robot teams has enabled complex tasks to be performed, but at the cost of requiring a large amount of exploration. Exchanging information …
This paper presents an advice mechanism compatible with heterogeneous advisers that incorporates advice into the advisee's policy via a method guaranteeing convergence to an …