A Switching Q-Learning Approach Focusing on Partial States.

Keinosuke Matsumoto Taisuke Ikimi Naoki Mori

Published in: MIM (2013)

Keyphrases

reinforcement learning
cooperative
state space
function approximation
multi agent
learning algorithm
state action
state variables
optimal policy
action selection
state transitions
markov decision problems
neural network
state information
single agent
model free
learning rate