Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models

Feb-18-2026, 15:13:30 GMT–Neural Information Processing Systems

The in-context learning (ICL) capability of pre-trained models based on the transformer architecture has received growing interest in recent years.

large language model, machine learning, reinforcement learning, (19 more...)

Neural Information Processing Systems

Feb-18-2026, 15:13:30 GMT

Conferences PDF

Country:
- Europe > United Kingdom
  - England > Cambridgeshire > Cambridge (0.04)
- North America > United States
  - Pennsylvania (0.04)
  - Virginia (0.04)

Genre:
- Research Report > Experimental Study (0.92)

Industry:
- Leisure & Entertainment > Games (1.00)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning
      - Neural Networks > Deep Learning (0.66)
      - Reinforcement Learning (1.00)
    - Natural Language > Large Language Model (0.88)
    - Representation & Reasoning > Agents (0.93)
  - Game Theory (1.00)

Duplicate Docs Excel Report

Title
Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models

Similar Docs Excel Report more

Title	Similarity	Source
None found