Modular Architecture for StarCraft II with Deep Reinforcement Learning.
Dennis LeeHaoran TangJeffrey O. ZhangHuazhe XuTrevor DarrellPieter AbbeelPublished in: AIIDE (2018)
Keyphrases
- modular architecture
- reinforcement learning
- function approximation
- state space
- temporal difference
- learning algorithm
- dynamic programming
- supervised learning
- conceptual framework
- databases
- multi agent reinforcement learning
- learning classifier systems
- optimal control
- domain knowledge
- learning process
- multi agent
- object oriented
- model free
- loosely coupled
- markov decision process
- machine learning
- database
- opponent modeling