Login / Signup

Provably Efficient Reinforcement Learning via Surprise Bound.

Hanlin ZhuRuosong WangJason D. Lee
Published in: CoRR (2023)
Keyphrases
  • reinforcement learning
  • worst case
  • upper bound
  • lightweight
  • database
  • neural network
  • machine learning
  • learning algorithm
  • decision making
  • markov decision processes