activity
20112021
most citedCompetitive Coevolution through Evolutionary Complexification

415 citations · 760 across the 9 of their papers we have counts for

collaborators

18 papers

cs.LG2021

Towards Consistent Predictive Confidence through Fitted Ensembles

Navid Kardan, Ankit Sharma, Kenneth O. Stanley

Deep neural networks are behind many of the recent successes in machine learning applications. However, these models can produce overconfident decisions while encountering out-of-d…

cs.LG20204 cited

Synthetic Petri Dish: A Novel Surrogate Model for Rapid Architecture Search

Aditya Rawal, Joel Lehman, Felipe Petroski Such +2

Neural Architecture Search (NAS) explores a large space of architectural motifs -- a compute-intensive process that often involves ground-truth evaluation of each motif by instanti…

cs.NE202042 cited

Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions

Rui Wang, Joel Lehman, Aditya Rawal +4

Creating open-ended algorithms, which generate their own never-ending stream of novel and appropriately challenging learning opportunities, could help to automate and accelerate pr…

cs.LG2020

Fiber: A Platform for Efficient Development and Distributed Training for Reinforcement Learning and Population-Based Methods

Jiale Zhi, Rui Wang, Jeff Clune +1

Recent advances in machine learning are consistently enabled by increasing amounts of computation. Reinforcement learning (RL) and population-based methods in particular pose uniqu…

cs.LG202069 cited

Learning to Continually Learn

Shawn Beaulieu, Lapo Frati, Thomas Miconi +4

Continual lifelong learning requires an agent or model to learn many sequentially ordered tasks, building on previous knowledge without catastrophically forgetting it. Much work ha…

cs.NE2020

Deep Innovation Protection: Confronting the Credit Assignment Problem in Training Heterogeneous Neural Architectures

Sebastian Risi, Kenneth O. Stanley

Deep reinforcement learning approaches have shown impressive results in a variety of different domains, however, more complex heterogeneous architectures such as world models requi…