Provable Safe Reinforcement Learning with Binary Feedback.
Andrew BennettDipendra MisraNathan KallusPublished in: CoRR (2022)
Keyphrases
- case study
- reinforcement learning
- reinforcement learning algorithms
- state space
- robotic control
- relevance feedback
- user feedback
- supervised learning
- optimal policy
- transfer learning
- function approximation
- feedback mechanisms
- hamming distance
- learning classifier systems
- special case
- function approximators
- non binary
- genetic algorithm
- policy search
- autonomous learning
- reinforcement learning methods
- temporal difference learning
- feedback loop
- multi agent
- machine learning
- multi agent systems