Diversifying AI: Towards Creative Chess with AlphaZero

by   Tom Zahavy, et al.

In recent years, Artificial Intelligence (AI) systems have surpassed human intelligence in a variety of computational tasks. However, AI systems, like humans, make mistakes, have blind spots, hallucinate, and struggle to generalize to new situations. This work explores whether AI can benefit from creative decision-making mechanisms when pushed to the limits of its computational rationality. In particular, we investigate whether a team of diverse AI systems can outperform a single AI in challenging tasks by generating more ideas as a group and then selecting the best ones. We study this question in the game of chess, the so-called drosophila of AI. We build on AlphaZero (AZ) and extend it to represent a league of agents via a latent-conditioned architecture, which we call AZ_db. We train AZ_db to generate a wider range of ideas using behavioral diversity techniques and select the most promising ones with sub-additive planning. Our experiments suggest that AZ_db plays chess in diverse ways, solves more puzzles as a group and outperforms a more homogeneous team. Notably, AZ_db solves twice as many challenging puzzles as AZ, including the challenging Penrose positions. When playing chess from different openings, we notice that players in AZ_db specialize in different openings, and that selecting a player for each opening using sub-additive planning results in a 50 Elo improvement over AZ. Our findings suggest that diversity bonuses emerge in teams of AI agents, just as they do in teams of humans and that diversity is a valuable asset in solving computationally hard problems.


page 1

page 10

page 26

page 27

page 29

page 35

page 36

page 42


On the Effect of Information Asymmetry in Human-AI Teams

Over the last years, the rising capabilities of artificial intelligence ...

Generative Personas That Behave and Experience Like Humans

Using artificial intelligence (AI) to automatically test a game remains ...

Gliders2012: Development and Competition Results

The RoboCup 2D Simulation League incorporates several challenging featur...

Modeling Human-AI Team Decision Making

AI and humans bring complementary skills to group deliberations. Modelin...

Human-centered mechanism design with Democratic AI

Building artificial intelligence (AI) that aligns with human values is a...

Questioning the impact of AI and interdisciplinarity in science: Lessons from COVID-19

Artificial intelligence (AI) has emerged as one of the most promising te...

Approximation Models of Combat in StarCraft 2

Real-time strategy (RTS) games make heavy use of artificial intelligence...

Please sign up or login with your details

Forgot password? Click here to reset