Login / Signup

Active preference-based Gaussian process regression for reward learning and optimization.

Erdem BiyikNicolas HuynhMykel J. KochenderferDorsa Sadigh
Published in: Int. J. Robotics Res. (2024)
Keyphrases
  • gaussian process regression
  • reinforcement learning
  • learning algorithm
  • learning process
  • prior knowledge
  • supervised learning
  • learning tasks
  • incremental learning
  • latent variables