Login / Signup

Learning Reward Functions for Robotic Manipulation by Observing Humans.

Minttu AlakuijalaGabriel Dulac-ArnoldJulien MairalJean PonceCordelia Schmid
Published in: CoRR (2022)
Keyphrases
  • inverse reinforcement learning
  • learning algorithm
  • prior knowledge
  • reinforcement learning
  • active learning
  • supervised learning
  • statistical model
  • imitation learning