Modeling the Centaur: Human-Machine Synergy in Sequential Decision Making

TL;DR

This paper explores human-machine synergy in chess, demonstrating how a mixture of experts approach can identify relative advantages and improve decision-making, revealing limitations of human expertise and the potential of reinforcement learning.

Contribution

It introduces a novel MoE-based framework for modeling human-machine teams in chess and analyzes the mechanisms of advantage identification and synergy.

Findings

High potential for human-machine synergy in chess.

Experts quickly saturate in advantage identification.

Reinforcement learning outperforms human experts in recognizing advantages.

Abstract

The field of collective intelligence studies how teams can achieve better results than any of the team members alone. The special case of human-machine teams carries unique challenges in this regard. For example, human teams often achieve synergy by communicating to discover their relative advantages, which is not an option if the team partner is an unexplainable deep neural network. Between 2005-2008 a set of "freestyle" chess tournaments were held, in which human-machine teams known as "centaurs", outperformed the best humans and best machines alone. Centaur players reported that they identified relative advantages between themselves and their chess program, even though the program was superhuman. Inspired by this and leveraging recent open-source models, we study human-machine like teams in chess. A human behavioral clone ("Maia") and a pure self-play RL-trained chess engine ("Leela") were composed into a team using a Mixture of Experts (MoE) architecture. By directing our research question at the selection mechanism of the MoE, we could isolate the issue of extracting relative advantages without knowledge sharing. We show that in principle, there is high potential for synergy between human and machine in a complex sequential decision environment such as chess. Furthermore, we show that an expert can identify only a small part of these relative advantages, and that the contribution of its subject matter expertise in doing so saturates quickly. This is probably due to the "curse of knowledge" phenomenon. We also train a network to recognize relative advantages using reinforcement learning, without chess expertise, and it outdoes the expert. Our experiments are repeated in asymmetric teams, in which identifying relative advantages is more challenging. Our findings contribute to the study of collective intelligence and human-centric AI.