Time-Based Reward Shaping in Real-Time Strategy Games.

Martin Midtgaard Lars Vinther Jeppe R. Christiansen Allan M. Christensen Yifeng Zeng

Published in: ADMI (2010)

Keyphrases

real time strategy games
reward shaping
reinforcement learning
multi agent
complex domains
case based planning
reinforcement learning algorithms
state space
markov decision problems
imperfect information
domain knowledge
semi supervised
optimal policy
model free
decision processes
objective function
knowledge base