Login / Signup

State-Space Support for Path-Based Reward Variables.

W. Douglas Obal IIWilliam H. Sanders
Published in: Perform. Evaluation (1999)
Keyphrases
  • state space
  • reinforcement learning
  • state variables
  • dynamical systems
  • optimal policy
  • variable selection
  • neural network
  • machine learning
  • case study
  • probabilistic model
  • random variables
  • stochastic domains