Gerald Tesauro

TD-Gammon

• Developed TD-Gammon, a backgammon program that achieved world-championship level play through self-play and temporal difference learning.
• Contributed to the field of reinforcement learning, a key area in AI.
• Works at IBM, continuing research in artificial intelligence and machine learning.

Gerald J. Tesauro is an American computer scientist and researcher at IBM. He is renowned for creating TD-Gammon, a groundbreaking backgammon program that learned to play at a world-championship level through self-play, a significant milestone in the field of artificial intelligence.

Milestones

• 1992
  Expert Systems and the Knowledge Boom Research

  The Neural Network That Mastered Backgammon

  Gerald Tesauro's TD-Gammon taught itself to play backgammon at world-champion level, proving neural networks could discover strategies humans never imagined.

  1992

← All people