QUOTA: The Quantile Option Architecture for Reinforcement Learning.
Shangtong ZhangHengshuai YaoPublished in: AAAI (2019)
Keyphrases
- reinforcement learning
- learning capabilities
- function approximation
- model free
- multi agent
- software architecture
- real time
- optimal policy
- distributed architecture
- network architecture
- management system
- markov decision processes
- supervised learning
- dynamic programming
- web services
- reinforcement learning algorithms
- decision making
- machine learning