A Reinforcement Learning Method for Maximizing Undiscounted Rewards

This publication has 6 references indexed in Scilit:

• Q-learning
  Machine Learning, 1992
• Using Transitional Proximity for Faster Reinforcement Learning
  Published by Elsevier ,1992
• Transfer of Learning by Composing Solutions of Elemental Sequential Tasks
  Machine Learning, 1992
• Quasimorphisms or Queasymorphisms? Modeling Finite Automaton Environments
  Published by Elsevier ,1991
• Integrated Architectures for Learning, Planning, and Reacting Based on Approximating Dynamic Programming
  Published by Elsevier ,1990
• Discrete Dynamic Programming
  The Annals of Mathematical Statistics, 1962