Login / Signup

Analysis of a Method Improving Reinforcement Learning Agents' Policies.

Daisuke KitakoshiHiroyuki ShioyaMasahito Kurihara
Published in: J. Adv. Comput. Intell. Intell. Informatics (2003)
Keyphrases
  • pairwise
  • data mining
  • dynamic programming
  • machine learning
  • decision trees
  • training data
  • objective function