Publication Details

SELECT * FROM publications WHERE Record_Number=11131
Reference TypeConference Proceedings
Author(s)Koert, D.; Maeda, G.; Neumann, G.; Peters, J.
TitleLearning Coupled Forward-Inverse Models with Combined Prediction Errors
Journal/Conference/Book TitleProceedings of the International Conference on Robotics and Automation (ICRA)
AbstractChallenging tasks in unstructured environments require robots to learn complex models. Given a large amount of information, learning multiple simple models can offer an efficient alternative to a monolithic complex network. Training multiple models---that is, learning their parameters and their responsibilities---has been shown to be prohibitively hard as optimization is prone to local minima. To efficiently learn multiple models for different contexts, we thus develop a new algorithm based on expectation maximization (EM). In contrast to comparable concepts, this algorithm trains multiple modules of paired forward-inverse models by using the prediction errors of both forward and inverse models simultaneously. In particular, we show that our method yields a substantial improvement over only considering the errors of the forward models on tasks where the inverse space contains multiple solutions.
Link to PDF


zum Seitenanfang