AI apology: interactive multi-objective reinforcement learning for human-aligned AI.
Hadassah HarlandRichard DazeleyBahareh NakisaFrancisco CruzPeter VamplewPublished in: Neural Comput. Appl. (2023)
Keyphrases
- multi objective
- artificial intelligence
- reinforcement learning
- ai community
- ai systems
- case based reasoning
- expert systems
- machine learning
- human level
- human intelligence
- machine intelligence
- intelligent systems
- artificially intelligent
- evolutionary algorithm
- computational intelligence
- human subjects
- knowledge representation
- decision making
- optimization algorithm
- multi objective optimization
- model free
- learning process
- trade off
- intelligent behavior
- computer science
- ai technologies
- learning algorithm