Login / Signup

Minimax Optimal Online Imitation Learning via Replay Estimation.

Gokul SwamyNived RajaramanMatthew PengSanjiban ChoudhuryJ. Andrew BagnellZhiwei Steven WuJiantao JiaoKannan Ramchandran
Published in: CoRR (2022)
Keyphrases
  • imitation learning
  • worst case
  • computer vision
  • real time
  • image sequences
  • reinforcement learning
  • dynamic programming
  • upper bound
  • optimal control