Argumentative Reward Learning: Reasoning About Human Preferences.
Francis Rhys WardFrancesco BelardinelliFrancesca ToniPublished in: CoRR (2022)
Keyphrases
- learning systems
- human learning
- learning algorithm
- learning process
- language acquisition
- inverse reinforcement learning
- reinforcement learning
- unsupervised learning
- learning objects
- learning tasks
- learning problems
- human experts
- solving problems
- learning capabilities
- supervised learning
- learning agent
- neural network