Login / Signup

Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis.

Koulik KhamaruAshwin PananjadyFeng RuanMartin J. WainwrightMichael I. Jordan
Published in: SIAM J. Math. Data Sci. (2021)
Keyphrases
  • temporal difference learning
  • reinforcement learning
  • dynamic programming
  • machine learning
  • optimal solution
  • learning environment
  • learning process
  • fixed point