Sign in

Using plan-based reward shaping to learn strategies in StarCraft: Broodwar.

Kyriakos EfthymiadisDaniel Kudenko
Published in: CIG (2013)
Keyphrases
  • reward shaping
  • complex domains
  • reinforcement learning
  • optimal strategy
  • search strategies
  • function approximation
  • agent learns
  • linear programming
  • software agents
  • decision theoretic