%Aigaion2 BibTeX export from Idiap Publications %Wednesday 06 November 2024 12:55:04 AM @INPROCEEDINGS{Tanwani_IROS_2013, author = {Tanwani, Ajay Kumar and Billard, Aude}, projects = {Idiap}, month = nov, title = {Transfer in Inverse Reinforcement Learning for Multiple Strategies}, booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems}, year = {2013}, pages = {3244-3250}, publisher = {IEEE}, location = {Tokyo, Japan}, url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6696817}, doi = {10.1109/IROS.2013.6696817}, abstract = {We consider the problem of incrementally learning different strategies of performing a complex sequential task from multiple demonstrations of an expert or a set of experts. While the task is the same, each expert differs in his/her way of performing it. We assume that this variety across experts' demonstration is due to the fact that each expert/strategy is driven by a different reward function, where reward function is expressed as a linear combination of a set of known features. Consequently, we can learn all the expert strategies by forming a convex set of optimal deterministic policies, from which one can match any unseen expert strategy drawn from this set. Instead of learning from scratch every optimal policy in this set, the learner transfers knowledge from the set of learned policies to bootstrap its search for new optimal policy. We demonstrate our approach on a simulated mini-golf task where the 7 degrees of freedom Barrett WAM robot arm learns to sequentially putt on different holes in accordance with the playing strategies of the expert.} }