Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Kenneth O. Stanley

Kenneth O. Stanley

Towards Consistent Predictive Confidence through Fitted Ensembles


Jun 22, 2021
Navid Kardan, Ankit Sharma, Kenneth O. Stanley

Figure 1 for Towards Consistent Predictive Confidence through Fitted Ensembles
Figure 2 for Towards Consistent Predictive Confidence through Fitted Ensembles
Figure 3 for Towards Consistent Predictive Confidence through Fitted Ensembles
Figure 4 for Towards Consistent Predictive Confidence through Fitted Ensembles
* IJCNN 2021 
  Access Paper or Ask Questions

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

Figure 1 for Synthetic Petri Dish: A Novel Surrogate Model for Rapid Architecture Search
Figure 2 for Synthetic Petri Dish: A Novel Surrogate Model for Rapid Architecture Search
Figure 3 for Synthetic Petri Dish: A Novel Surrogate Model for Rapid Architecture Search
Figure 4 for Synthetic Petri Dish: A Novel Surrogate Model for Rapid Architecture Search

  Access Paper or Ask Questions

First return then explore


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

Figure 1 for First return then explore
Figure 2 for First return then explore
Figure 3 for First return then explore
Figure 4 for First return then explore
* 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

Figure 1 for Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions
Figure 2 for Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions
Figure 3 for Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions
Figure 4 for Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions
* 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

Figure 1 for Fiber: A Platform for Efficient Development and Distributed Training for Reinforcement Learning and Population-Based Methods
Figure 2 for Fiber: A Platform for Efficient Development and Distributed Training for Reinforcement Learning and Population-Based Methods
Figure 3 for Fiber: A Platform for Efficient Development and Distributed Training for Reinforcement Learning and Population-Based Methods

  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

Figure 1 for Learning to Continually Learn
Figure 2 for Learning to Continually Learn
Figure 3 for Learning to Continually Learn
Figure 4 for Learning to Continually Learn

  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

Figure 1 for Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity
Figure 2 for Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity
Figure 3 for Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity
Figure 4 for Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity
* 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

Figure 1 for Improving Deep Neuroevolution via Deep Innovation Protection
Figure 2 for Improving Deep Neuroevolution via Deep Innovation Protection
Figure 3 for Improving Deep Neuroevolution via Deep Innovation Protection
Figure 4 for Improving Deep Neuroevolution via Deep Innovation Protection

  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

Figure 1 for Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data
Figure 2 for Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data
Figure 3 for Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data
Figure 4 for Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data

  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

Figure 1 for Evolvability ES: Scalable and Direct Optimization of Evolvability
Figure 2 for Evolvability ES: Scalable and Direct Optimization of Evolvability
Figure 3 for Evolvability ES: Scalable and Direct Optimization of Evolvability
Figure 4 for Evolvability ES: Scalable and Direct Optimization of Evolvability
* 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

Figure 1 for Go-Explore: a New Approach for Hard-Exploration Problems
Figure 2 for Go-Explore: a New Approach for Hard-Exploration Problems
Figure 3 for Go-Explore: a New Approach for Hard-Exploration Problems
Figure 4 for Go-Explore: a New Approach for Hard-Exploration Problems
* 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

Figure 1 for Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
Figure 2 for Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
Figure 3 for Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
Figure 4 for Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
* 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

Figure 1 for Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents
Figure 2 for Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents
Figure 3 for Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents
Figure 4 for Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents

  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

Figure 1 for The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities
Figure 2 for The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities
Figure 3 for The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities
Figure 4 for The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities

  Access Paper or Ask Questions

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


Aug 08, 2018
Andrea Soltoggio, Kenneth O. Stanley, Sebastian Risi

Figure 1 for Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks
Figure 2 for Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks
Figure 3 for Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks
Figure 4 for Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks
* Neural Networks, 2018 
  Access Paper or Ask Questions

Differentiable plasticity: training plastic neural networks with backpropagation


Jul 31, 2018
Thomas Miconi, Jeff Clune, Kenneth O. Stanley

Figure 1 for Differentiable plasticity: training plastic neural networks with backpropagation
Figure 2 for Differentiable plasticity: training plastic neural networks with backpropagation
Figure 3 for Differentiable plasticity: training plastic neural networks with backpropagation
Figure 4 for Differentiable plasticity: training plastic neural networks with backpropagation
* Proceedings of the 35th International Conference on Machine Learning (ICML2018), Stockholm, Sweden, PMLR 80, 2018 
 * Presented at ICML 2018 
  Access Paper or Ask Questions

Fitted Learning: Models with Awareness of their Limits


Jul 09, 2018
Navid Kardan, Kenneth O. Stanley

Figure 1 for Fitted Learning: Models with Awareness of their Limits
Figure 2 for Fitted Learning: Models with Awareness of their Limits
Figure 3 for Fitted Learning: Models with Awareness of their Limits
Figure 4 for Fitted Learning: Models with Awareness of their Limits

  Access Paper or Ask Questions

VINE: An Open Source Interactive Data Visualization Tool for Neuroevolution


May 03, 2018
Rui Wang, Jeff Clune, Kenneth O. Stanley

Figure 1 for VINE: An Open Source Interactive Data Visualization Tool for Neuroevolution
Figure 2 for VINE: An Open Source Interactive Data Visualization Tool for Neuroevolution
Figure 3 for VINE: An Open Source Interactive Data Visualization Tool for Neuroevolution
Figure 4 for VINE: An Open Source Interactive Data Visualization Tool for Neuroevolution

  Access Paper or Ask Questions

ES Is More Than Just a Traditional Finite-Difference Approximator


May 01, 2018
Joel Lehman, Jay Chen, Jeff Clune, Kenneth O. Stanley

Figure 1 for ES Is More Than Just a Traditional Finite-Difference Approximator
Figure 2 for ES Is More Than Just a Traditional Finite-Difference Approximator
Figure 3 for ES Is More Than Just a Traditional Finite-Difference Approximator
Figure 4 for ES Is More Than Just a Traditional Finite-Difference Approximator

  Access Paper or Ask Questions

Safe Mutations for Deep and Recurrent Neural Networks through Output Gradients


May 01, 2018
Joel Lehman, Jay Chen, Jeff Clune, Kenneth O. Stanley

Figure 1 for Safe Mutations for Deep and Recurrent Neural Networks through Output Gradients
Figure 2 for Safe Mutations for Deep and Recurrent Neural Networks through Output Gradients
Figure 3 for Safe Mutations for Deep and Recurrent Neural Networks through Output Gradients
Figure 4 for Safe Mutations for Deep and Recurrent Neural Networks through Output Gradients

  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

Figure 1 for Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
Figure 2 for Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
Figure 3 for Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
Figure 4 for Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning

  Access Paper or Ask Questions

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


Dec 18, 2017
Xingwen Zhang, Jeff Clune, Kenneth O. Stanley

Figure 1 for On the Relationship Between the OpenAI Evolution Strategy and Stochastic Gradient Descent
Figure 2 for On the Relationship Between the OpenAI Evolution Strategy and Stochastic Gradient Descent
Figure 3 for On the Relationship Between the OpenAI Evolution Strategy and Stochastic Gradient Descent
Figure 4 for On the Relationship Between the OpenAI Evolution Strategy and Stochastic Gradient Descent

  Access Paper or Ask Questions

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


Apr 17, 2017
Joost Huizinga, Kenneth O. Stanley, Jeff Clune

* SI can be found at: http://www.evolvingai.org/files/SI.zip 
  Access Paper or Ask Questions

A Proposed Infrastructure for Adding Online Interaction to Any Evolutionary Domain


Jul 11, 2014
Paul Szerlip, Kenneth O. Stanley

Figure 1 for A Proposed Infrastructure for Adding Online Interaction to Any Evolutionary Domain
* Presented at WebAL-1: Workshop on Artificial Life and the Web 2014 (arXiv:1406.2507) 
  Access Paper or Ask Questions

Unsupervised Feature Learning through Divergent Discriminative Feature Accumulation


Jun 10, 2014
Paul A. Szerlip, Gregory Morse, Justin K. Pugh, Kenneth O. Stanley

Figure 1 for Unsupervised Feature Learning through Divergent Discriminative Feature Accumulation
Figure 2 for Unsupervised Feature Learning through Divergent Discriminative Feature Accumulation
* Corrected citation formatting 
  Access Paper or Ask Questions

Evolvability Is Inevitable: Increasing Evolvability Without the Pressure to Adapt


Feb 05, 2013
Joel Lehman, Kenneth O. Stanley

Figure 1 for Evolvability Is Inevitable: Increasing Evolvability Without the Pressure to Adapt
Figure 2 for Evolvability Is Inevitable: Increasing Evolvability Without the Pressure to Adapt
Figure 3 for Evolvability Is Inevitable: Increasing Evolvability Without the Pressure to Adapt
Figure 4 for Evolvability Is Inevitable: Increasing Evolvability Without the Pressure to Adapt

  Access Paper or Ask Questions