Login / Signup

Improving Optimality of Neural Rewards Regression for Data-Efficient Batch Near-Optimal Policy Identification.

Daniel SchneegaßSteffen UdluftThomas Martinetz
Published in: ICANN (1) (2007)
Keyphrases
  • optimal policy
  • dynamic programming
  • markov decision processes
  • probability distribution
  • data mining
  • decision making
  • state space