Kenneth O. Stanley

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

May 27, 2020
Aditya Rawal, Joel Lehman, Felipe Petroski Such, Jeff Clune, Kenneth O. Stanley

Access Paper or Ask Questions

First return then explore

May 14, 2020
Adrien Ecoffet, Joost Huizinga, Joel Lehman, Kenneth O. Stanley, Jeff Clune

* 45 pages, 13 figures, 4 tables; reorganized sections and modified SI text extensively

Access Paper or Ask Questions

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

Apr 13, 2020
Rui Wang, Joel Lehman, Aditya Rawal, Jiale Zhi, Yulun Li, Jeff Clune, Kenneth O. Stanley

* 23 pages, 14 figures

Access Paper or Ask Questions

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

Mar 25, 2020
Jiale Zhi, Rui Wang, Jeff Clune, Kenneth O. Stanley

Access Paper or Ask Questions

Learning to Continually Learn

Mar 04, 2020
Shawn Beaulieu, Lapo Frati, Thomas Miconi, Joel Lehman, Kenneth O. Stanley, Jeff Clune, Nick Cheney

Access Paper or Ask Questions

Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity

Feb 24, 2020
Thomas Miconi, Aditya Rawal, Jeff Clune, Kenneth O. Stanley

* 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019
* Presented at the 7th International Conference on Learning Representations (ICLR 2019)

Access Paper or Ask Questions

Improving Deep Neuroevolution via Deep Innovation Protection

Dec 29, 2019
Sebastian Risi, Kenneth O. Stanley

Access Paper or Ask Questions

Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data

Dec 17, 2019
Felipe Petroski Such, Aditya Rawal, Joel Lehman, Kenneth O. Stanley, Jeff Clune

Access Paper or Ask Questions

An Overview of Open-Ended Evolution: Editorial Introduction to the Open-Ended Evolution II Special Issue

Sep 10, 2019
Norman Packard, Mark A. Bedau, Alastair Channon, Takashi Ikegami, Steen Rasmussen, Kenneth O. Stanley, Tim Taylor

* Artificial Life, 25(2), pp. 93-103, 2019
* This article is published in the Artificial Life journal (https://www.mitpressjournals.org/loi/artl) and is copyright (c) 2019 Massachusetts Institute of Technology. It it posted on arXiv.org after the publication embargo period in accordance with MIT Press Journals' author posting guidelines (https://www.mitpressjournals.org/for_authors#authorposting)

Access Paper or Ask Questions

Evolvability ES: Scalable and Direct Optimization of Evolvability

Jul 13, 2019
Alexander Gajewski, Jeff Clune, Kenneth O. Stanley, Joel Lehman

* Published in GECCO 2019

Access Paper or Ask Questions

Go-Explore: a New Approach for Hard-Exploration Problems

Jan 30, 2019
Adrien Ecoffet, Joost Huizinga, Joel Lehman, Kenneth O. Stanley, Jeff Clune

* 37 pages, 14 figures

Access Paper or Ask Questions

Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions

Jan 09, 2019
Rui Wang, Joel Lehman, Jeff Clune, Kenneth O. Stanley

* 27 pages, 8 figures

Access Paper or Ask Questions

Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents

Oct 29, 2018
Edoardo Conti, Vashisht Madhavan, Felipe Petroski Such, Joel Lehman, Kenneth O. Stanley, Jeff Clune

Access Paper or Ask Questions

The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities

Aug 14, 2018
Joel Lehman, Jeff Clune, Dusan Misevic, Christoph Adami, Lee Altenberg, Julie Beaulieu, Peter J. Bentley, Samuel Bernard, Guillaume Beslon, David M. Bryson, Patryk Chrabaszcz, Nick Cheney, Antoine Cully, Stephane Doncieux, Fred C. Dyer, Kai Olav Ellefsen, Robert Feldt, Stephan Fischer, Stephanie Forrest, Antoine Frénoy, Christian Gagné, Leni Le Goff, Laura M. Grabowski, Babak Hodjat, Frank Hutter, Laurent Keller, Carole Knibbe, Peter Krcah, Richard E. Lenski, Hod Lipson, Robert MacCurdy, Carlos Maestre, Risto Miikkulainen, Sara Mitri, David E. Moriarty, Jean-Baptiste Mouret, Anh Nguyen, Charles Ofria, Marc Parizeau, David Parsons, Robert T. Pennock, William F. Punch, Thomas S. Ray, Marc Schoenauer, Eric Shulte, Karl Sims, Kenneth O. Stanley, François Taddei, Danesh Tarapore, Simon Thibault, Westley Weimer, Richard Watson, Jason Yosinski

Access Paper or Ask Questions

Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning

Apr 20, 2018
Felipe Petroski Such, Vashisht Madhavan, Edoardo Conti, Joel Lehman, Kenneth O. Stanley, Jeff Clune

Access Paper or Ask Questions

Kenneth O. Stanley

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

First return then explore

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

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

Learning to Continually Learn

Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity

Improving Deep Neuroevolution via Deep Innovation Protection

Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data

An Overview of Open-Ended Evolution: Editorial Introduction to the Open-Ended Evolution II Special Issue

Evolvability ES: Scalable and Direct Optimization of Evolvability

Go-Explore: a New Approach for Hard-Exploration Problems

Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions

Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents

The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities

Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks

Differentiable plasticity: training plastic neural networks with backpropagation

Fitted Learning: Models with Awareness of their Limits

VINE: An Open Source Interactive Data Visualization Tool for Neuroevolution

ES Is More Than Just a Traditional Finite-Difference Approximator

Safe Mutations for Deep and Recurrent Neural Networks through Output Gradients

Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning

On the Relationship Between the OpenAI Evolution Strategy and Stochastic Gradient Descent

The Emergence of Canalization and Evolvability in an Open-Ended, Interactive Evolutionary System

A Proposed Infrastructure for Adding Online Interaction to Any Evolutionary Domain

Unsupervised Feature Learning through Divergent Discriminative Feature Accumulation

Evolvability Is Inevitable: Increasing Evolvability Without the Pressure to Adapt

Exploring Promising Stepping Stones by Combining Novelty Search with Interactive Evolution