Modular Architecture for StarCraft II with Deep Reinforcement Learning.
Dennis LeeHaoran TangJeffrey O. ZhangHuazhe XuTrevor DarrellPieter AbbeelPublished in: CoRR (2018)
Keyphrases
- modular architecture
- reinforcement learning
- function approximation
- conceptual framework
- loosely coupled
- reinforcement learning algorithms
- learning algorithm
- markov decision processes
- robotic control
- model free
- search engine
- action space
- temporal difference learning
- multi agent reinforcement learning
- policy search
- supervised learning
- optimal policy
- state space
- dynamic programming
- multi agent
- temporal difference
- knowledge base
- reinforcement learning methods
- machine learning
- databases