Can I read Human-AI Cooperation Insights on EtoBox?

Human-AI Cooperation Insights by Nikolay Khachatryan is a document available to read on EtoBox.

What is Human-AI Cooperation Insights about?

This paper aims to understand human-AI cooperation through game theory and reinforcement learning models. It conducts an empirical study comparing different reinforcement learning algorithms (Vanilla Policy Gradient, Proximal Policy Optimization, and Deep Q-Network) and game theory scenarios (Hawk Dove and Prisoners dilemma) in a large-scale human-AI experiment. The results found that the Deep Q-Network algorithm and Hawk Dove scenario elicited significantly higher levels of cooperation between humans and A

Author

Nikolay Khachatryan

Language

EN