Learning Policies for Contextual Submodular Prediction
Stéphane RossJiaji ZhouYisong YueDebadeepta DeyJ. Andrew BagnellPublished in: CoRR (2013)
Keyphrases
- learning algorithm
- learning process
- reinforcement learning
- greedy algorithm
- contextual information
- learning systems
- information systems
- learning scenarios
- energy minimization
- learning problems
- prediction accuracy
- learning experience
- learning tasks
- knowledge acquisition
- artificial neural networks
- knowledge base
- learning scheme