论文信息 - SWIRL: A SequentialWindowed Inverse Reinforcement Learning Algorithm for Robot Tasks With Delayed Rewards - 字舞流文

SWIRL: A SequentialWindowed Inverse Reinforcement Learning Algorithm for Robot Tasks With Delayed Rewards

Brijen Thananjeyan | Sanjay Krishnan | Kenneth Y. Goldberg | Animesh Garg | Richard Liaw | Florian T. Pokorny | Lauren Miller | S. Krishnan | Ken Goldberg | Richard Liaw | Animesh Garg | Lauren Miller | Brijen Thananjeyan

[1] Jan Peters,et al. Learning movement primitive attractor goals and sequential skills from kinesthetic demonstrations , 2015, Robotics Auton. Syst..

[2] Pieter Abbeel,et al. Learning for control from multiple demonstrations , 2008, ICML '08.

[3] Pieter Abbeel,et al. Apprenticeship learning via inverse reinforcement learning , 2004, ICML.

[4] Brett Browning,et al. A survey of robot learning from demonstration , 2009, Robotics Auton. Syst..