Benchmarks and Algorithms for Offline Preference-Based Reward Learning.
Daniel ShinAnca D. DraganDaniel S. BrownPublished in: Trans. Mach. Learn. Res. (2023)
Keyphrases
- learning algorithm
- reinforcement learning
- noise tolerant
- learning process
- significant improvement
- online learning
- optimization problems
- active learning
- computational complexity
- real time
- learning systems
- learning tasks
- learning models
- data structure
- learning problems
- computational cost
- clustering algorithm
- machine learning
- machine learning algorithms
- orders of magnitude
- data sets