Sanjay Krishnan, Animesh Garg, Richard Liaw, Brijen Thananjeyan, Lauren Miller, Florian T. Pokorny, Ken Goldberg. SWIRL: A SequentialWindowed Inverse Reinforcement Learning Algorithm for Robot Tasks With Delayed Rewards. In Ken Goldberg, Pieter Abbeel, Kostas Bekris, Lauren Miller, editors, Algorithmic Foundations of Robotics XII, Proceedings of the Twelfth Workshop on the Algorithmic Foundations of Robotics, WAFR 2016, San Francisco, California, USA, December 18-20, 2016. Volume 13 of Springer Proceedings in Advanced Robotics, pages 672-687, Springer, 2016. [doi]
Abstract is missing.