Bayesian Q-learning with Assumed Density Filtering.

Heejin Jeong Daniel D. Lee

Published in: CoRR (2017)

Keyphrases

reinforcement learning
multi agent
state space
function approximation
cooperative
bayesian estimation
bayesian networks
potential field

learning rate
learning algorithm
model free
filtering algorithm
machine learning
posterior probability
maximum likelihood
stochastic approximation

multi agent reinforcement learning
bayesian filtering
median filter
bayesian learning
reinforcement learning algorithms
optimal policy
action selection

decision theory
adaptive filtering
reinforcement learning methods
information filtering
posterior distribution
multi agent systems
bucket brigade