Modeling and imitating human behaviors, actions and decisions from visual data are crucial for the future of AI, yet problematic due to the complexity of humans. In this project, the goal is proposing approaches to model and imitate humans in a generative manner. Thanks to its well adaptation ability to new scenarios, deep reinforcement learning (DRL) would be the key component. The other keystone of the project would be the recent computer vision (CV) models in order to understand and interpret humans from visual perception.