LogiLaw Dataset Towards Reinforcement Learning from Logical Feedback (RLLF).
Ha-Thanh NguyenWachara FungwacharakornKen SatohPublished in: JURIX (2023)
Keyphrases
- reinforcement learning
- function approximation
- database
- state space
- reinforcement learning algorithms
- benchmark datasets
- machine learning
- training dataset
- synthetic datasets
- markov decision processes
- databases
- optimal policy
- relevance feedback
- real world
- real life
- video sequences
- training data
- knowledge base
- model free
- logical representation
- logical operations
- active exploration
- robotic control