Provably Efficient Neural GTD for Off-Policy Learning.
Hoi-To WaiZhuoran YangZhaoran WangMingyi HongPublished in: NeurIPS (2020)
Keyphrases
- active learning
- learning systems
- learning algorithm
- social networks
- prior knowledge
- neural computation
- learning scenarios
- online learning
- worst case
- reinforcement learning
- case study
- neural network
- learning process
- decision trees
- artificial intelligence
- knowledge acquisition
- information retrieval
- mobile learning
- network architecture
- learning scheme
- efficient learning
- neural model
- real time