Login / Signup

EANT+KALMAN: An Efficient Reinforcement Learning Method for Continuous State Partially Observable Domains.

Yohannes KassahunJose de GeaJan Hendrik MetzenMark EdgingtonFrank Kirchner
Published in: KI (2008)
Keyphrases
  • reinforcement learning
  • dynamic programming
  • state space
  • continuous state
  • policy search
  • partially observable domains
  • model free
  • decision making
  • computational complexity
  • random walk