Login / Signup

An analytic solution to discrete Bayesian reinforcement learning.

Pascal PoupartNikos A. VlassisJesse HoeyKevin Regan
Published in: ICML (2006)
Keyphrases
  • bayesian reinforcement learning
  • monte carlo tree search
  • optimal policy
  • bayesian networks
  • reinforcement learning
  • decision problems
  • finite number
  • partially observable markov decision processes