Neural Contextual Bandits with UCB-based Exploration.
Dongruo ZhouLihong LiQuanquan GuPublished in: ICML (2020)
Keyphrases
- multi armed bandit
- multi armed bandits
- network architecture
- contextual information
- bandit problems
- nonlinear predictive control
- neural network
- associative memory
- context sensitive
- multi armed bandit problems
- e learning
- information systems
- connectionist models
- biologically plausible
- database
- active exploration
- real world
- social networks
- neural computation
- artificial neural
- interactive exploration
- website
- neural model
- learning rules
- search strategies
- optimal solution
- reinforcement learning