no code implementations • 10 Mar 2020 • Bohan Wu, Feng Xu, Zhanpeng He, Abhi Gupta, Peter K. Allen
This paper aims to address this scalability challenge with a robust, sample-efficient, and general meta-IRL algorithm, SQUIRL, that performs a new but related long-horizon task robustly given only a single video demonstration.
no code implementations • 8 Mar 2019 • Bohan Wu, Iretiayo Akinola, Peter K. Allen
Recent advances in on-policy reinforcement learning (RL) methods enabled learning agents in virtual environments to master complex tasks with high-dimensional and continuous observation and action spaces.
1 code implementation • 29 Jun 2018 • Iretiayo Akinola, Jacob Varley, Boyuan Chen, Peter K. Allen
This framework greatly improves the performance of standard online grasp planning algorithms by incorporating a notion of reachability into the online grasp planning process.
Robotics