Improper Learning with Gradient-based Policy Optimization.
Mohammadi ZakiAvinash MohanAditya GopalanShie MannorPublished in: CoRR (2021)
Keyphrases
- learning process
- learning tasks
- reinforcement learning
- learning systems
- prior knowledge
- active learning
- online learning
- learning scheme
- optimization problems
- incremental learning
- action selection
- feature selection
- learning community
- global optimization
- optimal policy
- knowledge acquisition
- evolutionary algorithm
- case study
- decision trees