Forest Agostinelli's research involves designing new artificial intelligence algorithms and applying these algorithms to problems in the sciences. Simultaneously, his research draws upon the sciences to provide inspiration for new artificial intelligence algorithms.
His research interests include:
Deep learning: Neural network architectures, learning activation functions
Reinforcement learning: deep RL, model-based RL
Search: Learning heuristics, large state spaces, theoretical guarantees
Interpretability/Explainability
His application interests include:
Logic: Puzzle solving, theorem proving
Bioinformatics: Circadian rhythms, protein folding
Neuroscience: Hippocampus and memory
High energy physics: Identifying exotic particles
Chemistry: Molecular optimization, retrosynthesis