Combining Dynamic Reward Shaping and Action Shaping for Coordinating Multi-agent Learning.

Xiangbin Zhu Chongjie Zhang Victor R. Lesser

Published in: IAT (2013)

Keyphrases

reward shaping
complex domains
multi agent learning
reinforcement learning
reinforcement learning algorithms
domain theory
state space
markov decision problems
game theory
function approximation
neural network
dynamic environments
knowledge base
linear programming
optimal policy