Learning Human Rewards by Inferring Their Latent Intelligence Levels in Multi-Agent Games: A Theory-of-Mind Approach with Application to Driving Data.
Ran TianMasayoshi TomizukaLiting SunPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- multi agent
- data sets
- data structure
- data analysis
- data sources
- training data
- database
- prior knowledge
- machine learning
- data collection
- learning algorithm
- learning process
- human subjects
- human experts
- learning agents
- learning models
- data quality
- artificial intelligence
- human activities
- game theory
- background knowledge
- data mining techniques
- active learning