Beating humans in a penny-matching game by leveraging cognitive hierarchy theory and Bayesian learning

Abstract

It is a long-standing goal of artificial intelligence (AI) to be superior to human beings in decision making. Games are suitable for testing AI capabilities of making good decisions in non-numerical tasks. In this paper, we develop a new AI algorithm to play the penny-matching game considered in Shannon's "mind-reading machine" (1953) against human players. In particular, we exploit cognitive hierarchy theory and Bayesian learning techniques to continually evolve a model for predicting human player decisions, and let the AI player make decisions according to the model predictions to pursue the best chance of winning. Experimental results show that our AI algorithm beats 27 out of 30 volunteer human players.

Anytime Game-Theoretic Planning with Active Reasoning About Humans' Latent States for Human-Centered Robots

“…Hence, the latent states' transition model is reduced to P(θ t+1 |θ t , st , σ)=I(θ t+1 =θ t ). In general repeated games, the transition model can be represented as a Markov chain and its parameters σ can be embedded in the POMDP and learned simultaneously as in [41]. High-level robot planning.…”

Hierarchical and Game-Theoretic Decision-Making for Connected and Automated Vehicles in Overtaking Scenarios

“…The level-K framework characterizes agents' strategies according to their depth of reasoning, denoted as "level." It models agents' interactions based on the assumption that a level-K player makes optimal decisions while considering the other agents as level-(K−1) players [18]- [20]. In this paper, we employ the level-K framework to design a racing controller for a leading robot that is chased by a following robot who is attempting to overtake [21].…”