Login / Signup

RIRL: A Recurrent Imitation and Reinforcement Learning Method for Long-Horizon Robotic Tasks.

Zhitao YuJian ZhangShiwen MaoSenthilkumar C. G. PeriaswamyJustin Patton
Published in: CCNC (2022)
Keyphrases
  • reinforcement learning
  • objective function
  • real time
  • dynamic programming
  • domain specific
  • model checking
  • markov decision processes