Projects

Research

• Lookahead Optimizer: k steps forward, 1 step back
  • Michael R. Zhang, James Lucas, Geoffrey Hinton, Jimmy Ba
  • Neural Information Processing Systems 2019
  • Code / Slides
• Reverse Curriculum Generation for Reinforcement Learning
  • Carlos Florensa, David Held, Markus Wulfmeier, Michael Zhang, Pieter Abbeel
  • Conference on Robot Learning (CoRL) 2017
  • Website
• Probabilistically Safe Policy Transfer
  • David Held, Zoe McCarthy, Michael Zhang, Fred Shentu, Pieter Abbeel
  • International Conference on Robotics and Automation (ICRA) 2017