Login / Signup

Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate.

Dongjie YuWenjun ZouYujie YangHaitong MaShengbo Eben LiJingliang DuanJianyu Chen
Published in: CoRR (2022)
Keyphrases
  • model based reinforcement learning
  • markov decision processes
  • state space
  • reinforcement learning
  • incomplete information
  • conditional probabilities