TD-Gammon
Description
TD-Gammon is a game-learning architecture for playing backgammon. It involves the use of a learning algorithm and a feedforward neural network.
Papers Using This Method
On-line Policy Improvement using Monte-Carlo Search2025-01-09Model Predictive Control and Reinforcement Learning: A Unified Framework Based on Dynamic Programming2024-06-02Search in Imperfect Information Games2021-11-10A Hierarchical Reinforcement Learning Method for Persistent Time-Sensitive Tasks2016-06-20