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

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

    • Research
    • Fellowship Programs
    • Grants
    • 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
Navigate
  • About
  • Events
  • AI Glossary
  • Careers
  • Search
Participate
  • Get Involved
  • Support HAI
  • Contact Us

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

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

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.

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

Related Events

Eyck Freymann | AI and Strategic Stability: A Framework for U.S.–China Technology Competition
SeminarMay 27, 202612:00 PM - 1:15 PM
May
27
2026

Strategic stability exists when neither side thinks it can improve its strategic outcome by striking first.

Seminar

Eyck Freymann | AI and Strategic Stability: A Framework for U.S.–China Technology Competition

May 27, 202612:00 PM - 1:15 PM

Strategic stability exists when neither side thinks it can improve its strategic outcome by striking first.

2026 RAISE Health Symposium
Jun 02, 2026
June
02
2026

The 2026 RAISE Health Symposium will convene leading voices in technology, medicine, and policy to explore what’s real, what’s next, and what’s needed to ensure AI advances responsibly and benefits all. Registration opens March 11.

Event

2026 RAISE Health Symposium

Jun 02, 2026

The 2026 RAISE Health Symposium will convene leading voices in technology, medicine, and policy to explore what’s real, what’s next, and what’s needed to ensure AI advances responsibly and benefits all. Registration opens March 11.

Juan Sebastián Gómez-Cañón | Challenges And Opportunities For Human-Centered Music Emotion Recognition
SeminarJun 03, 202612:00 PM - 1:15 PM
June
03
2026

Music is intertwined with human emotion, memory, and identity, making it a powerful medium for affective experience and regulation.

Seminar

Juan Sebastián Gómez-Cañón | Challenges And Opportunities For Human-Centered Music Emotion Recognition

Jun 03, 202612:00 PM - 1:15 PM

Music is intertwined with human emotion, memory, and identity, making it a powerful medium for affective experience and regulation.

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