Scalable lifelong reinforcement learning.
Yusen ZhanHaitham Bou-AmmarMatthew E. TaylorPublished in: Pattern Recognit. (2017)
Keyphrases
- reinforcement learning
- function approximation
- state space
- web scale
- multi agent
- learning process
- st century
- highly scalable
- multi agent reinforcement learning
- multi agent systems
- temporal difference learning
- optimal control
- competence development
- reinforcement learning methods
- robot control
- technology enhanced learning
- model free
- real time
- learning problems
- supervised learning
- social networks
- real world