Modeling Affect-based Intrinsic Rewards for Exploration and Learning.
Dean ZadokDaniel McDuffAshish KapoorPublished in: ICRA (2021)
Keyphrases
- reinforcement learning
- learning algorithm
- real time
- online learning
- prior knowledge
- learning systems
- action selection
- learning tasks
- case study
- background knowledge
- learning process
- elementary school
- learning problems
- unsupervised learning
- knowledge acquisition
- supervised learning
- artificial neural networks
- website
- information systems
- artificial intelligence
- data mining