Benchmarks and Algorithms for Offline Preference-Based Reward Learning.
Daniel ShinAnca D. DraganDaniel S. BrownPublished in: CoRR (2023)
Keyphrases
- learning algorithm
- learning process
- reinforcement learning
- online learning
- real time
- learning models
- learning systems
- significant improvement
- optimization problems
- noise tolerant
- orders of magnitude
- prior knowledge
- active learning
- supervised learning
- neural network
- computational cost
- data structure
- unsupervised learning
- computationally efficient
- benchmark datasets
- evolutionary algorithm
- mobile learning
- learning tasks
- learning problems
- decision trees
- machine learning
- automatically learned