Stanford
University
  • Stanford Home
  • Maps & Directions
  • Search Stanford
  • Emergency Info
  • Terms of Use
  • Privacy
  • Copyright
  • Trademarks
  • Non-Discrimination
  • Accessibility
© Stanford University.  Stanford, California 94305.
Wolfgang Lehrach | Code World Models for General Game Playing | Stanford HAI
Skip to content
  • About

    • About
    • People
    • Get Involved with HAI
    • Support HAI
    • Subscribe to Email
  • Research

    • Research
    • Research Programs
    • Grants
    • Marlowe (opens in new tab)
    • Student Affinity Groups
    • Centers & Labs
    • Research Publications
    • Research Partners
  • Education

    • Education
    • Executive and Professional Education
    • Government and Policymakers
    • K-12
    • Stanford Students
  • Policy

    • Policy
    • Policy Publications
    • Policymaker Education
    • Student Opportunities
  • AI Index

    • AI Index
    • AI Index Report
    • Global Vibrancy Tool
    • People
  • News
  • Events
  • Industry
  • Centers & Labs

Stay Up To Date

Get the latest news, advances in research, policy work, and education program updates from HAI in your inbox weekly.

Sign Up For Latest News

Navigate
  • About
  • Events
  • AI Glossary
  • Careers
  • Search
Participate
  • Get Involved
  • Support HAI
  • Contact Us
Your browser does not support the video tag.
eventSeminar

Wolfgang Lehrach | Code World Models for General Game Playing

Status
Past
Date
Wednesday, May 13, 2026 12:00 PM - 1:15 PM PST/PDT
Location
353 Jane Stanford Way, Stanford, CA, 94305 | Room 119
Topics
Machine Learning
Natural Language Processing
Attend Virtually
Overview
Watch event recording

While Large Language Models (LLMs) show promise in many domains, relying on them for direct policy generation in games often results in illegal moves and poor strategic play.

Overview
Watch event recording
Share
Link copied to clipboard!
Event Contact
Stanford HAI
stanford-hai@stanford.edu

Related Events

Neil Thompson: Forecasting AI’s Impact on Human Expertise and the Future of Work
Oct 12, 202612:00 PM - 1:00 PM
October
12
2026

AI is advancing rapidly at the cognitive tasks that make up knowledge work, raising fears among firms, policymakers, and, not least, workers of a “China shock” for white-collar jobs. Neil Thompson will present new research on whether those fears are warranted.

Event

Neil Thompson: Forecasting AI’s Impact on Human Expertise and the Future of Work

Oct 12, 202612:00 PM - 1:00 PM

AI is advancing rapidly at the cognitive tasks that make up knowledge work, raising fears among firms, policymakers, and, not least, workers of a “China shock” for white-collar jobs. Neil Thompson will present new research on whether those fears are warranted.

Daniel Rock | The Free Hypothesis: AI and Shifted Bottlenecks in Science
Oct 26, 202612:00 PM - 1:00 PM
October
26
2026

Scientific progress is a key driver of economic growth and prosperity. There is great excitement- but also concerns- about the impacts of AI on science, but so far little data. We provide early insights on this from three data sources: a sample of 15 million Gemini interactions, an inventory of over 2,600 specialized AI models across disciplines, and a survey of over 600 scientists.

Event

Daniel Rock | The Free Hypothesis: AI and Shifted Bottlenecks in Science

Oct 26, 202612:00 PM - 1:00 PM

Scientific progress is a key driver of economic growth and prosperity. There is great excitement- but also concerns- about the impacts of AI on science, but so far little data. We provide early insights on this from three data sources: a sample of 15 million Gemini interactions, an inventory of over 2,600 specialized AI models across disciplines, and a survey of over 600 scientists.

In this talk, I present an approach that moves away from direct prompting, instead using LLMs as program synthesizers to bridge the gap between natural language rules and symbolic world models.  The LLM receives a game description and example trajectories, and outputs an executable, symbolic world model (CWM) represented in Python. The trajectories also ensure the rules are correctly captured and aid in refining the CWM if they are not.  Note that even trajectories containing only a single player's observations and actions can be used to help validate and refine CWMs.  Furthermore, partially observed trajectories also allow comparisons between CWMs via a bound on the likelihood.  


Given a CWM, Monte Carlo Tree Search (MCTS) or Reinforcement Learning (RL) methods can play the game, and gameplay can be further enhanced by adding in LLM-derived synthesized value functions. Imperfect information games are handled by having the LLM synthesize inference functions to impute information sets, or by directly training reinforcement learning policies on top of the CWM.

Speaker
Wolfgang Lehrach
Staff Research Scientist, DeepMind