Login / Signup

Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism.

Ming YinYaqi DuanMengdi WangYu-Xiang Wang
Published in: CoRR (2022)
Keyphrases
  • reinforcement learning
  • information sources
  • partial information
  • prior knowledge
  • domain knowledge
  • information processing
  • data sets
  • higher level
  • standard deviation
  • information overload
  • graphical representation