Login / Signup

Differentiable Logic Policy for Interpretable Deep Reinforcement Learning: A Study From an Optimization Perspective.

Xin LiHaojie LeiLi ZhangMingzhong Wang
Published in: IEEE Trans. Pattern Anal. Mach. Intell. (2023)
Keyphrases
  • reinforcement learning
  • optimization algorithm
  • function approximation
  • viewpoint
  • empirical studies
  • loss function
  • neural network
  • machine learning
  • logic programming
  • optimal policy
  • optimization process
  • policy search