Search Results - dimitri+bertsekas

2 Results Sort By:
Superior Computer Chess with Model Predictive Control, Reinforcement Learning, and Rollout Algorithms
Modern AI for strategic games including chess has evolved from early rule-based systems such as brute force engines that relied on handcrafted heuristics and exhaustive search, to sophisticated learning-based methods that can create and refine their own strategies. Reinforcement learning (RL) programs including Alpha Zero mastered chess starting with...
Published: 9/9/2025   |   Inventor(s): Dimitri Bertsekas, Yuchao Li, Atharva Gundawar
Keywords(s):  
Category(s): Artificial Intelligence/Machine Learning, Computing & Information Technology, Physical Science
Enhancing Sequence Generation with Rollout Algorithms
Background Generative pre-trained transformers (GPT) have grown in recent years in a number of natural language processing applications, largely due to the powerful openly available software and easy-to-use natural language interfaces. Transformers can provide a flexible and powerful model that generalizes the earlier forms of neural networks by using...
Published: 5/20/2025   |   Inventor(s): Dimitri Bertsekas, Yuchao Li
Keywords(s):  
Category(s): Physical Science, Wireless & Networking, Artificial Intelligence/Machine Learning