Login / Signup

Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning.

Yi ZhaoRinu BoneyAlexander IlinJuho KannalaJoni Pajarinen
Published in: ESANN (2022)
Keyphrases
  • adaptive behavior
  • reinforcement learning
  • online learning
  • real time
  • function approximation
  • state space
  • learning experience
  • learning environment
  • dynamic programming