Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero

• URL: http://arxiv.org/abs/2310.16410v1
• Date: Wed, 25 Oct 2023 06:49:26 GMT
• Title: Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero
• Authors: Lisa Schut, Nenad Tomasev, Tom McGrath, Demis Hassabis, Ulrich Paquet, Been Kim
• Abstract summary: We show how to extract new chess concepts from AlphaZero, an AI system that mastered the game of chess via self-play without human supervision. In a human study, we show that these concepts are learnable by top human experts, as four top chess grandmasters show improvements in solving the presented concept prototype positions. This marks an important first milestone in advancing the frontier of human knowledge by leveraging AI.
• Score: 10.569213003371654
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Artificial Intelligence (AI) systems have made remarkable progress, attaining super-human performance across various domains. This presents us with an opportunity to further human knowledge and improve human expert performance by leveraging the hidden knowledge encoded within these highly performant AI systems. Yet, this knowledge is often hard to extract, and may be hard to understand or learn from. Here, we show that this is possible by proposing a new method that allows us to extract new chess concepts in AlphaZero, an AI system that mastered the game of chess via self-play without human supervision. Our analysis indicates that AlphaZero may encode knowledge that extends beyond the existing human knowledge, but knowledge that is ultimately not beyond human grasp, and can be successfully learned from. In a human study, we show that these concepts are learnable by top human experts, as four top chess grandmasters show improvements in solving the presented concept prototype positions. This marks an important first milestone in advancing the frontier of human knowledge by leveraging AI; a development that could bear profound implications and help us shape how we interact with AI systems across many AI applications.

Related papers

• Imagining and building wise machines: The centrality of AI metacognition [78.76893632793497]
  We argue that shortcomings stem from one overarching failure: AI systems lack wisdom. While AI research has focused on task-level strategies, metacognition is underdeveloped in AI systems. We propose that integrating metacognitive capabilities into AI systems is crucial for enhancing their robustness, explainability, cooperation, and safety.
  arXiv  Detail & Related papers  (2024-11-04T18:10:10Z)
• Maia-2: A Unified Model for Human-AI Alignment in Chess [10.577896749797485]
  We propose a unified modeling approach for human-AI alignment in chess. We introduce a skill-aware attention mechanism to dynamically integrate players' strengths with encoded chess positions. Our results pave the way for deeper insights into human decision-making and AI-guided teaching tools.
  arXiv  Detail & Related papers  (2024-09-30T17:54:23Z)
• Close the Gates: How we can keep the future human by choosing not to develop superhuman general-purpose artificial intelligence [0.20919309330073077]
  In the coming years, humanity may irreversibly cross a threshold by creating general-purpose AI. This would upend core aspects of human society, present many unprecedented risks, and is likely to be uncontrollable in several senses. We can choose to not do so, starting by instituting hard limits on the computation that can be used to train and run neural networks. With these limits in place, AI research and industry can focus on making both narrow and general-purpose AI that humans can understand and control, and from which we can reap enormous benefit.
  arXiv  Detail & Related papers  (2023-11-15T23:41:12Z)
• AI for Mathematics: A Cognitive Science Perspective [86.02346372284292]
  Mathematics is one of the most powerful conceptual systems developed and used by the human species. Rapid progress in AI, particularly propelled by advances in large language models (LLMs), has sparked renewed, widespread interest in building such systems.
  arXiv  Detail & Related papers  (2023-10-19T02:00:31Z)
• Towards Human Cognition Level-based Experiment Design for Counterfactual Explanations (XAI) [68.8204255655161]
  The emphasis of XAI research appears to have turned to a more pragmatic explanation approach for better understanding. An extensive area where cognitive science research may substantially influence XAI advancements is evaluating user knowledge and feedback. We propose a framework to experiment with generating and evaluating the explanations on the grounds of different cognitive levels of understanding.
  arXiv  Detail & Related papers  (2022-10-31T19:20:22Z)
• The Embeddings World and Artificial General Intelligence [2.28438857884398]
  We argue that pre-trained embeddings play a key role in building this intelligent world. We discuss how pre-trained embeddings facilitate achieving several characteristics of human-level intelligence.
  arXiv  Detail & Related papers  (2022-09-14T11:56:30Z)
• Making AI 'Smart': Bridging AI and Cognitive Science [0.0]
  With the integration of cognitive science, the 'artificial' characteristic of Artificial Intelligence might soon be replaced with'smart' This will help develop more powerful AI systems and simultaneously gives us a better understanding of how the human brain works. We argue that the possibility of AI taking over human civilization is low as developing such an advanced system requires a better understanding of the human brain first.
  arXiv  Detail & Related papers  (2021-12-31T09:30:44Z)
• Instructive artificial intelligence (AI) for human training, assistance, and explainability [0.24629531282150877]
  We show how a neural network might instruct human trainees as an alternative to traditional approaches to explainable AI (XAI) An AI examines human actions and calculates variations on the human strategy that lead to better performance. Results will be presented on AI instruction's ability to improve human decision-making and human-AI teaming in Hanabi.
  arXiv  Detail & Related papers  (2021-11-02T16:46:46Z)
• Trustworthy AI: A Computational Perspective [54.80482955088197]
  We focus on six of the most crucial dimensions in achieving trustworthy AI: (i) Safety & Robustness, (ii) Non-discrimination & Fairness, (iii) Explainability, (iv) Privacy, (v) Accountability & Auditability, and (vi) Environmental Well-Being. For each dimension, we review the recent related technologies according to a taxonomy and summarize their applications in real-world systems.
  arXiv  Detail & Related papers  (2021-07-12T14:21:46Z)
• The MineRL BASALT Competition on Learning from Human Feedback [58.17897225617566]
  The MineRL BASALT competition aims to spur forward research on this important class of techniques. We design a suite of four tasks in Minecraft for which we expect it will be hard to write down hardcoded reward functions. We provide a dataset of human demonstrations on each of the four tasks, as well as an imitation learning baseline.
  arXiv  Detail & Related papers  (2021-07-05T12:18:17Z)
• Future Trends for Human-AI Collaboration: A Comprehensive Taxonomy of AI/AGI Using Multiple Intelligences and Learning Styles [95.58955174499371]
  We describe various aspects of multiple human intelligences and learning styles, which may impact on a variety of AI problem domains. Future AI systems will be able not only to communicate with human users and each other, but also to efficiently exchange knowledge and wisdom.
  arXiv  Detail & Related papers  (2020-08-07T21:00:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.