The Entropy Of Artificial Intelligence And A Case Study Of Alphazero From Shannon's Perspective

Abstract

The recently released AlphaZero algorithm achieves superhuman performance in the games of chess, shogi and Go, which raises two open questions. Firstly, as there is a finite number of possibilities in the game, is there a quantifiable intelligence measurement for evaluating intelligent systems, e.g. AlphaZero? Secondly, AlphaZero introduces sophisticated reinforcement learning and self-play to efficiently encode the possible states, is there a simple information-theoretic model to represent the learning process and offer more insights in fostering strong AI systems? This paper explores the above two questions by proposing a simple variance of Shannon's communication model, the concept of intelligence entropy and the Unified Intelligence-Communication Model is proposed, which provide an information-theoretic metric for investigating the intelligence level and also provide an bound for intelligent agents in the form of Shannon's capacity, namely, the intelligence capacity. This paper t

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2018the

Related papers

• Impartial Games: A Challenge For Reinforcement Learning (2022)0.00
• Are Alphazero-like Agents Robust To Adversarial Perturbations? (2022)0.00
• ELF Opengo: An Analysis And Open Reimplementation Of Alphazero (2019)0.00
• Alphastar: An Evolutionary Computation Perspective (2019)15.13
• A Mathematical Theory Of Agency And Intelligence (2026)0.00
• Alphazero-edu: Democratizing Access To Alphazero (2025)0.00
• Scaling Laws For A Multi-agent Reinforcement Learning Model (2022)0.00
• Frontier Coding Agents Can Now Implement An Alphazero Self-play Machine Learning Pipeline For Connect Four That Performs Comparably To An External Solver (2026)0.00