ORL-AUDITOR: Dataset Auditing in Offline Deep Reinforcement Learning.
Linkang DuMin ChenMingyang SunShouling JiPeng ChengJiming ChenZhikun ZhangPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- real time
- face recognition
- feature extraction
- benchmark datasets
- linear discriminant analysis
- database
- subspace methods
- optimal policy
- face identification
- face databases
- facial images
- feature set
- learning algorithm
- markov decision processes
- action selection
- training dataset
- robotic control
- face images
- supervised learning
- state space
- dynamic programming
- object recognition
- training data
- decision trees