1 citations · 1 across the 4 of their papers we have counts for
4 papers
Low Rank Factorizations are Indirect Encodings for Deep Neuroevolution
Jack Garbus, Jordan Pollack
Deep neuroevolution is a highly scalable alternative to reinforcement learning due to its unique ability to encode network updates in a small number of bytes. Recent insights from…
Phylogeny-Informed Interaction Estimation Accelerates Co-Evolutionary Learning
Jack Garbus, Thomas Willkens, Alexander Lalejini +1
Co-evolution is a powerful problem-solving approach. However, fitness evaluation in co-evolutionary algorithms can be computationally expensive, as the quality of an individual in…
Runtime phylogenetic analysis enables extreme subsampling for test-based problems
Alexander Lalejini, Marcos Sanson, Jack Garbus +2
A phylogeny describes the evolutionary history of an evolving population. Evolutionary search algorithms can perfectly track the ancestry of candidate solutions, illuminating a pop…
Emergent Resource Exchange and Tolerated Theft Behavior using Multi-Agent Reinforcement Learning
Jack Garbus, Jordan Pollack
For decades, the evolution of cooperation has piqued the interest of numerous academic disciplines such as game theory, economics, biology, and computer science. In this work, we d…