Login / Signup

Transfer Method for Reinforcement Learning in Same Transition Model - Quick Approach and Preferential Exploration.

Toshiaki TakanoHaruhiko TakaseHiroharu KawanakaShinji Tsuruoka
Published in: ICMLA (1) (2011)
Keyphrases
  • transition model
  • reinforcement learning
  • dynamic programming
  • input output
  • markov model