Login / Signup

An Entropy-Guided Adaptive Co-construction Method of State and Action Spaces in Reinforcement Learning.

Masato NagayoshiHajime MuraoHisashi Tamaki
Published in: ICONIP (1) (2014)
Keyphrases
  • reinforcement learning
  • dynamic programming
  • machine learning
  • state space
  • bayesian networks
  • objective function
  • multi agent
  • computational complexity
  • np hard
  • state and action spaces