Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search.
Yuan TianQin WangZhiwu HuangWen LiDengxin DaiMinghao YangJun WangOlga FinkPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- efficient search
- search algorithm
- search space pruning
- computationally efficient
- search efficiency
- search strategy
- management system
- cost effective
- disk space
- efficient indexing
- learning capabilities
- computationally expensive
- real time
- search space
- image analysis
- search mechanism
- software architecture
- supervised learning
- state space
- search strategies
- information seeking
- query processing
- high quality
- database systems
- machine learning