Bidirectional Learning for Offline Infinite-width Model-based Optimization.
Can ChenYingxue ZhangJie FuXue LiuMark CoatesPublished in: CoRR (2022)
Keyphrases
- real time
- learning problems
- learning tasks
- learning systems
- average reward reinforcement learning
- learning algorithm
- reinforcement learning
- empirical studies
- data sets
- optimization algorithm
- unsupervised learning
- active learning
- prior knowledge
- evolutionary algorithm
- learning process
- information retrieval
- mobile robot
- optimization problems
- background knowledge
- expert systems
- case study
- learning analytics
- inductive inference