Login / Signup

Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification.

Takumi TanabeRei SatoKazuto FukuchiJun SakumaYouhei Akimoto
Published in: CoRR (2022)
Keyphrases
  • max min
  • lower bound
  • cost function
  • decision making
  • computational complexity
  • evolutionary algorithm
  • dynamic programming
  • worst case
  • combinatorial optimization
  • convergence rate
  • hill climbing