Login / Signup

Efficient Preference-based Reinforcement Learning via Aligned Experience Estimation.

Fengshuo BaiRui ZhaoHongming ZhangSijia CuiYing WenYaodong YangBo XuLei Han
Published in: CoRR (2024)
Keyphrases
  • reinforcement learning
  • machine learning
  • lightweight
  • decision problems
  • real time
  • neural network
  • parameter estimation
  • computationally expensive
  • robust estimation