Login / Signup

Forward and Backward State Abstractions for Off-policy Evaluation.

Meiling HaoPingfan SuLiyuan HuZoltan SzaboQingyuan ZhaoChengchun Shi
Published in: CoRR (2024)
Keyphrases
  • forward and backward
  • policy evaluation
  • state space
  • reinforcement learning
  • least squares
  • supervised learning
  • model free
  • neural network
  • optical flow
  • function approximation
  • temporal difference
  • greedy search