Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased.
Chao YuJiaxuan GaoWeilin LiuBotian XuHao TangJiaqi YangYu WangYi WuPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- learning algorithm
- supervised learning
- machine learning
- learning process
- solve complex tasks
- human agent interaction
- data sets
- learning tasks
- learning problems
- training data
- cooperative
- human subjects
- high quality
- case study
- computer vision
- unsupervised learning
- human experts
- minimax probability machine