Forest Agostinelli
About
Forest Agostinelli is an Assistant Professor in the Department of Computer Science and Engineering at the University of South Carolina, where he leads the Deep Reasoning Lab. His research lies at the intersection of Artificial Intelligence, Deep Learning, and Reinforcement Learning, with a specialized focus on Heuristic Search and Logic. He is widely recognized for his work on DeepCubeA, a deep reinforcement learning algorithm that independently learned to solve the Rubik’s Cube using a weighted $A^*$ search approach. Dr. Agostinelli’s work aims to create "Deep Reasoning" systems that combine the pattern recognition strengths of neural networks with the symbolic logic and planning capabilities of classical AI. This research has broad applications, from solving complex combinatorial problems and improving scientific discovery to optimizing chemical synthesis and enhancing automated theorem proving.
Research Performance Summary
First Recorded Paper
Adaptive multi-column deep neural networks with application to robust image denoising
Year: 2013
Citations: 337
Venue: Advances in neural information processing systems 26
Latest Recorded Paper
Stable Planning through Aligned Representations in Model-Based Reinforcement Learning
Year: 2025
Citations: 0
Venue: NeurIPS 2025 Workshop on Embodied World Models for Decision Making
Last 10 Years Publication Activity
This timeline shows the professor's yearly publication activity.