Treatment Policy Learning in Multiobjective Settings with Fully Observed Outcomes.
Sooraj BoominathanMichael OberstHelen ZhouSanjat KanjilalDavid A. SontagPublished in: CoRR (2020)
Keyphrases
- multi objective
- learning systems
- prior knowledge
- active learning
- learning tasks
- neural network
- decision trees
- reinforcement learning
- learning process
- evolutionary algorithm
- supervised learning
- optimization algorithm
- partially observable markov decision processes
- learning analytics
- learning problems
- differential evolution
- unsupervised learning
- trade off
- decision making
- learning algorithm