Search for tag: "reinforcement"

Strategic Mastery in Terminal: A Novel Reinforcement Learning Approach to Tower-Defense Gameplay, Shivam Kak, UG '26, Ishaan Javali, UG '26, Yagiz Devre, UG '26 (5EE515B6)

From chess to Atari to AlphaGo, performance in games has been a benchmark of performance for machine learning. Terminal is a tower-defense game where players submit algorithms that play against each…

From  Research Princeton Research Day 1 likes 27 plays

ECE-524 Session 21 | 4.25

From  Broadcast Broadcast Center Staff 0 likes 4 plays

NJ AI Summit - Foundations of AI

From  Broadcast Broadcast Center Staff 0 likes 114 plays

ECE-524 Session 17 | 4.09

From  Broadcast Broadcast Center Staff 0 likes 11 plays

PLI Symposium 11/28 Benjamin Eysenbach

From  Broadcast Broadcast Center Staff 0 likes 17 plays

PLI Symposium 11/28 Mengdi Wang

From  Broadcast Broadcast Center Staff 0 likes 25 plays

Agents with aspirations: A Prospect Theory approach to intrinsic motivation in Reinforcement Learning, Lucas James Irwin, UG '23 (2270745)

Artificial Intelligence (AI) is becoming ubiquitous, yet the lack of transparency in its decision-making process and its value system raises alarms. To address this, my senior thesis combines…

From  Research Princeton Research Day 1 likes 24 plays

Investigating Persuasiveness in Large Language Models, Promise Ekpo Osaine, GS

While the rate of progress and innovation in Artificial intelligence (AI) has many potential benefits, the potential for accidental deleterious effects cannot be overemphasised. It has been…

From  Research Princeton Research Day 2 likes 108 plays

How Nature’s Tiniest Soda Could Help Feed the World: The Story of the Algal Pyrenoid, Eric Franklin, G4 (3965535)

Plants are responsible for almost everything around us. Not just as crops for us or livestock to eat, but also for the wood that makes up our houses and furniture, the cotton that we wear as clothes,…

From  Research Princeton Research Day 6 likes 303 plays

Using a Theory of Human Cognition to Improve Computer Agents, Albert Lin, UG '23 (3965329)

Current reinforcement learning (RL) models still have difficulty generalizing to novel, but related, tasks. They are also often composed of deep neural networks which carry out computations that do…

From  Research Princeton Research Day 3 likes 67 plays

Panel Discussion: Data science at the energy-water nexus

Panelists will explore the nexus between energy and water, and big data, such as how energy and water are intertwined and how data science can help advance research and development and business…

From  Broadcast Broadcast Center Staff 0 likes 6 plays