Login / Signup

Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions.

Alejandro EscontrelaXue Bin PengWenhao YuTingnan ZhangAtil IscenKen GoldbergPieter Abbeel
Published in: IROS (2022)
Keyphrases
  • reward function
  • image sequences
  • machine learning
  • optical flow
  • moving objects
  • state space
  • complex systems
  • motion model
  • transition probabilities
  • transition model
  • policy search