Data-efficient Hindsight Off-policy Option Learning.
Markus WulfmeierDushyant RaoRoland HafnerThomas LampeAbbas AbdolmalekiTim HertweckMichael NeunertDhruva TirumalaNoah Y. SiegelNicolas HeessMartin A. RiedmillerPublished in: ICML (2021)
Keyphrases
- data sets
- prior knowledge
- data sources
- data processing
- learning process
- learning algorithm
- learning systems
- active learning
- image data
- computer systems
- data collection
- small number
- data points
- data structure
- training data
- database
- original data
- raw data
- data distribution
- background knowledge
- learning models
- historical data
- high dimensional data
- knowledge acquisition
- online learning
- input data
- supervised learning
- end users
- high quality
- machine learning