no code implementations • 13 Mar 2024 • SIMA Team, Maria Abi Raad, Arun Ahuja, Catarina Barros, Frederic Besse, Andrew Bolt, Adrian Bolton, Bethanie Brownfield, Gavin Buttimore, Max Cant, Sarah Chakera, Stephanie C. Y. Chan, Jeff Clune, Adrian Collister, Vikki Copeman, Alex Cullum, Ishita Dasgupta, Dario de Cesare, Julia Di Trapani, Yani Donchev, Emma Dunleavy, Martin Engelcke, Ryan Faulkner, Frankie Garcia, Charles Gbadamosi, Zhitao Gong, Lucy Gonzales, Kshitij Gupta, Karol Gregor, Arne Olav Hallingstad, Tim Harley, Sam Haves, Felix Hill, Ed Hirst, Drew A. Hudson, Jony Hudson, Steph Hughes-Fitt, Danilo J. Rezende, Mimi Jasarevic, Laura Kampis, Rosemary Ke, Thomas Keck, Junkyung Kim, Oscar Knagg, Kavya Kopparapu, Andrew Lampinen, Shane Legg, Alexander Lerchner, Marjorie Limont, YuLan Liu, Maria Loks-Thompson, Joseph Marino, Kathryn Martin Cussons, Loic Matthey, Siobhan Mcloughlin, Piermaria Mendolicchio, Hamza Merzic, Anna Mitenkova, Alexandre Moufarek, Valeria Oliveira, Yanko Oliveira, Hannah Openshaw, Renke Pan, Aneesh Pappu, Alex Platonov, Ollie Purkiss, David Reichert, John Reid, Pierre Harvey Richemond, Tyson Roberts, Giles Ruscoe, Jaume Sanchez Elias, Tasha Sandars, Daniel P. Sawyer, Tim Scholtes, Guy Simmons, Daniel Slater, Hubert Soyer, Heiko Strathmann, Peter Stys, Allison C. Tam, Denis Teplyashin, Tayfun Terzi, Davide Vercelli, Bojan Vujatovic, Marcus Wainwright, Jane X. Wang, Zhengdong Wang, Daan Wierstra, Duncan Williams, Nathaniel Wong, Sarah York, Nick Young
Building embodied AI systems that can follow arbitrary language instructions in any 3D environment is a key challenge for creating general AI.
no code implementations • 23 Feb 2024 • Jake Bruce, Michael Dennis, Ashley Edwards, Jack Parker-Holder, Yuge Shi, Edward Hughes, Matthew Lai, Aditi Mavalankar, Richie Steigerwald, Chris Apps, Yusuf Aytar, Sarah Bechtle, Feryal Behbahani, Stephanie Chan, Nicolas Heess, Lucy Gonzalez, Simon Osindero, Sherjil Ozair, Scott Reed, Jingwei Zhang, Konrad Zolna, Jeff Clune, Nando de Freitas, Satinder Singh, Tim Rocktäschel
We introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos.
no code implementations • 26 Oct 2023 • Yoshua Bengio, Geoffrey Hinton, Andrew Yao, Dawn Song, Pieter Abbeel, Yuval Noah Harari, Ya-Qin Zhang, Lan Xue, Shai Shalev-Shwartz, Gillian Hadfield, Jeff Clune, Tegan Maharaj, Frank Hutter, Atılım Güneş Baydin, Sheila Mcilraith, Qiqi Gao, Ashwin Acharya, David Krueger, Anca Dragan, Philip Torr, Stuart Russell, Daniel Kahneman, Jan Brauner, Sören Mindermann
In this short consensus paper, we outline risks from upcoming, advanced AI systems.
no code implementations • 19 Oct 2023 • Herbie Bradley, Andrew Dai, Hannah Teufel, Jenny Zhang, Koen Oostermeijer, Marco Bellagente, Jeff Clune, Kenneth Stanley, Grégory Schott, Joel Lehman
In many text-generation problems, users may prefer not only a single response, but a diverse range of high-quality outputs from which to choose.
1 code implementation • 18 Oct 2023 • Li Ding, Jenny Zhang, Jeff Clune, Lee Spector, Joel Lehman
Meanwhile, Quality Diversity (QD) algorithms excel at identifying diverse and high-quality solutions but often rely on manually crafted diversity metrics.
no code implementations • 12 Oct 2023 • Lapo Frati, Neil Traft, Jeff Clune, Nick Cheney
We show that our zapping procedure results in improved transfer accuracy and/or more rapid adaptation in both standard fine-tuning and continual learning settings, while being simple to implement and computationally efficient.
1 code implementation • 5 Jul 2023 • Ben Norman, Jeff Clune
We argue a core barrier prohibiting many RL approaches from learning intelligent exploration is that the methods attempt to explore and exploit simultaneously, which harms both exploration and exploitation as the goals often conflict.
1 code implementation • 2 Jun 2023 • Jenny Zhang, Joel Lehman, Kenneth Stanley, Jeff Clune
An Achilles Heel of open-endedness research is the inability to quantify (and thus prioritize) tasks that are not just learnable, but also $\textit{interesting}$ (e. g., worthwhile and novel).
1 code implementation • NeurIPS 2023 • Shengran Hu, Jeff Clune
We hypothesize one reason for such cognitive deficiencies is that they lack the benefits of thinking in language and that we can improve AI agents by training them to think like humans do.
2 code implementations • 23 Jun 2022 • Bowen Baker, Ilge Akkaya, Peter Zhokhov, Joost Huizinga, Jie Tang, Adrien Ecoffet, Brandon Houghton, Raul Sampedro, Jeff Clune
Pretraining on noisy, internet-scale datasets has been heavily studied as a technique for training models with broad, general capabilities for text, images, and other modalities.
no code implementations • 26 Aug 2021 • Shawn L. Beaulieu, Jeff Clune, Nick Cheney
Past efforts to engineer such systems have sought to build or regulate artificial neural networks using disjoint sets of weights that are uniquely sensitive to specific tasks or inputs.
no code implementations • 28 Jun 2021 • Ingmar Kanitscheider, Joost Huizinga, David Farhi, William Hebgen Guss, Brandon Houghton, Raul Sampedro, Peter Zhokhov, Bowen Baker, Adrien Ecoffet, Jie Tang, Oleg Klimov, Jeff Clune
An important challenge in reinforcement learning is training agents that can solve a wide variety of tasks.
1 code implementation • 12 Jun 2020 • Adrien Ecoffet, Jeff Clune, Joel Lehman
This paper proposes that open-ended evolution and artificial life have much to contribute towards the understanding of open-ended AI, focusing here in particular on the safety of open-ended search.
1 code implementation • 27 May 2020 • Aditya Rawal, Joel Lehman, Felipe Petroski Such, Jeff Clune, Kenneth O. Stanley
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 instantiating it within a large network, and training and evaluating the network with thousands of domain-specific data samples.
2 code implementations • 27 Apr 2020 • Adrien Ecoffet, Joost Huizinga, Joel Lehman, Kenneth O. Stanley, Jeff Clune
The promise of reinforcement learning is to solve complex sequential decision problems autonomously by specifying a high-level reward function only.
Ranked #1 on Atari Games on Atari 2600 Montezuma's Revenge
1 code implementation • 25 Mar 2020 • Jiale Zhi, Rui Wang, Jeff Clune, Kenneth O. Stanley
Recent advances in machine learning are consistently enabled by increasing amounts of computation.
1 code implementation • ICML 2020 • Rui Wang, Joel Lehman, Aditya Rawal, Jiale Zhi, Yulun Li, Jeff Clune, Kenneth O. Stanley
Creating open-ended algorithms, which generate their own never-ending stream of novel and appropriately challenging learning opportunities, could help to automate and accelerate progress in machine learning.
3 code implementations • 3 Mar 2020 • Cédric Colas, Joost Huizinga, Vashisht Madhavan, Jeff Clune
Quality-Diversity (QD) algorithms, and MAP-Elites (ME) in particular, have proven very useful for a broad range of applications including enabling real robots to recover quickly from joint damage, solving strongly deceptive maze tasks or evolving robot morphologies to discover new gaits.
no code implementations • ICLR 2019 • Thomas Miconi, Aditya Rawal, Jeff Clune, Kenneth O. Stanley
We show that neuromodulated plasticity improves the performance of neural networks on both reinforcement learning and supervised learning tasks.
5 code implementations • 21 Feb 2020 • Shawn Beaulieu, Lapo Frati, Thomas Miconi, Joel Lehman, Kenneth O. Stanley, Jeff Clune, Nick Cheney
Continual lifelong learning requires an agent or model to learn many sequentially ordered tasks, building on previous knowledge without catastrophically forgetting it.
3 code implementations • 17 Dec 2019 • Felipe Petroski Such, Aditya Rawal, Joel Lehman, Kenneth O. Stanley, Jeff Clune
This paper introduces GTNs, discusses their potential, and showcases that they can substantially accelerate learning.
1 code implementation • 22 Oct 2019 • Mohammad Sadegh Norouzzadeh, Dan Morris, Sara Beery, Neel Joshi, Nebojsa Jojic, Jeff Clune
However, the accuracy of results depends on the amount, quality, and diversity of the data available to train models, and the literature has focused on projects with millions of relevant, labeled training images.
1 code implementation • 13 Jul 2019 • Alexander Gajewski, Jeff Clune, Kenneth O. Stanley, Joel Lehman
Designing evolutionary algorithms capable of uncovering highly evolvable representations is an open challenge; such evolvability is important because it accelerates evolution and enables fast adaptation to changing circumstances.
no code implementations • 27 May 2019 • Jeff Clune
Because it it may be the fastest path to general AI and because it is inherently scientifically interesting to understand the conditions in which a simple algorithm can produce general AI (as happened on Earth where Darwinian evolution produced human intelligence), I argue that the pursuit of AI-GAs should be considered a new grand challenge of computer science research.
1 code implementation • 18 Apr 2019 • Anh Nguyen, Jason Yosinski, Jeff Clune
A neuroscience method to understanding the brain is to find and study the preferred stimuli that highly activate an individual cell or groups of cells.
3 code implementations • 30 Jan 2019 • Adrien Ecoffet, Joost Huizinga, Joel Lehman, Kenneth O. Stanley, Jeff Clune
Go-Explore can also harness human-provided domain knowledge and, when augmented with it, scores a mean of over 650k points on Montezuma's Revenge.
Ranked #1 on Atari Games on Atari 2600 Pitfall!
2 code implementations • 7 Jan 2019 • Rui Wang, Joel Lehman, Jeff Clune, Kenneth O. Stanley
Our results show that POET produces a diverse range of sophisticated behaviors that solve a wide range of environmental challenges, many of which cannot be solved by direct optimization alone, or even through a direct-path curriculum-building control algorithm introduced to highlight the critical role of open-endedness in solving ambitious challenges.
no code implementations • 27 Dec 2018 • Rowan McAllister, Gregory Kahn, Jeff Clune, Sergey Levine
Our method estimates an uncertainty measure about the model's prediction, taking into account an explicit (generative) model of the observation distribution to handle out-of-distribution inputs.
1 code implementation • 17 Dec 2018 • Felipe Petroski Such, Vashisht Madhavan, Rosanne Liu, Rui Wang, Pablo Samuel Castro, Yulun Li, Jiale Zhi, Ludwig Schubert, Marc G. Bellemare, Jeff Clune, Joel Lehman
We lessen this friction, by (1) training several algorithms at scale and releasing trained models, (2) integrating with a previous Deep RL model release, and (3) releasing code that makes it easy for anyone to load, visualize, and analyze such models.
3 code implementations • 9 Jul 2018 • Joost Huizinga, Jeff Clune
Lastly, we show that, in contrast to NSGA-II and Lexicase Selection, CMOEA can effectively leverage secondary objectives to achieve state-of-the-art results on the robotics task.
no code implementations • 1 Jun 2018 • Christopher Stanton, Jeff Clune
The strong performance of DeepCS on these sparse- and dense-reward tasks suggests that encouraging intra-life novelty is an interesting, new approach for improving performance in Deep RL and motivates further research into hybridizing across-training and intra-life exploration methods.
1 code implementation • 3 May 2018 • Rui Wang, Jeff Clune, Kenneth O. Stanley
Recent advances in deep neuroevolution have demonstrated that evolutionary algorithms, such as evolution strategies (ES) and genetic algorithms (GA), can scale to train deep neural networks to solve difficult reinforcement learning (RL) problems.
5 code implementations • ICML 2018 • Thomas Miconi, Jeff Clune, Kenneth O. Stanley
How can we build agents that keep learning from experience, quickly and efficiently, after their initial training?
no code implementations • 9 Mar 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
Biological evolution provides a creative fount of complex and subtle adaptations, often surprising the scientists who discover them.
2 code implementations • NeurIPS 2018 • Edoardo Conti, Vashisht Madhavan, Felipe Petroski Such, Joel Lehman, Kenneth O. Stanley, Jeff Clune
Evolution strategies (ES) are a family of black-box optimization algorithms able to train deep neural networks roughly as well as Q-learning and policy gradient methods on challenging deep reinforcement learning (RL) problems, but are much faster (e. g. hours vs. days) because they parallelize better.
no code implementations • 18 Dec 2017 • Xingwen Zhang, Jeff Clune, Kenneth O. Stanley
Because stochastic gradient descent (SGD) has shown promise optimizing neural networks with millions of parameters and few if any alternatives are known to exist, it has moved to the heart of leading approaches to reinforcement learning (RL).
14 code implementations • 18 Dec 2017 • Felipe Petroski Such, Vashisht Madhavan, Edoardo Conti, Joel Lehman, Kenneth O. Stanley, Jeff Clune
Here we demonstrate they can: we evolve the weights of a DNN with a simple, gradient-free, population-based genetic algorithm (GA) and it performs well on hard deep RL problems, including Atari and humanoid locomotion.
no code implementations • 18 Dec 2017 • Joel Lehman, Jay Chen, Jeff Clune, Kenneth O. Stanley
However, this ES optimizes for a different gradient than just reward: It optimizes for the average reward of the entire population, thereby seeking parameters that are robust to perturbation.
1 code implementation • 18 Dec 2017 • Joel Lehman, Jay Chen, Jeff Clune, Kenneth O. Stanley
While neuroevolution (evolving neural networks) has a successful track record across a variety of domains from reinforcement learning to artificial life, it is rarely applied to large, deep neural networks.
no code implementations • 20 May 2017 • Roby Velez, Jeff Clune
On the simple diagnostic problem from the prior work, diffusion-based neuromodulation 1) induces task-specific learning in groups of nodes and connections (task-specific localized learning), which 2) produces functional modules for each subtask, and 3) yields higher performance by eliminating catastrophic forgetting.
1 code implementation • 17 Apr 2017 • Joost Huizinga, Kenneth O. Stanley, Jeff Clune
In this paper we reveal a unique system in which canalization did emerge in computational evolution.
no code implementations • 16 Mar 2017 • Mohammed Sadegh Norouzzadeh, Anh Nguyen, Margaret Kosmala, Ali Swanson, Meredith Palmer, Craig Packer, Jeff Clune
Having accurate, detailed, and up-to-date information about the location and behavior of animals in the wild would revolutionize our ability to study and conserve ecosystems.
1 code implementation • CVPR 2017 • Anh Nguyen, Jeff Clune, Yoshua Bengio, Alexey Dosovitskiy, Jason Yosinski
PPGNs are composed of 1) a generator network G that is capable of drawing a wide range of image types and 2) a replaceable "condition" network C that tells the generator what to draw.
5 code implementations • NeurIPS 2016 • Anh Nguyen, Alexey Dosovitskiy, Jason Yosinski, Thomas Brox, Jeff Clune
Understanding the inner workings of such computational brains is both fascinating basic science that is interesting in its own right - similar to why we study the human brain - and will enable researchers to further improve DNNs.
no code implementations • 11 Feb 2016 • Anh Nguyen, Jason Yosinski, Jeff Clune
Here, we introduce an algorithm that explicitly uncovers the multiple facets of each neuron by producing a synthetic visualization of each of the types of images that activate a neuron.
1 code implementation • 24 Nov 2015 • Yixuan Li, Jason Yosinski, Jeff Clune, Hod Lipson, John Hopcroft
Recent success in training deep neural networks have prompted active investigation into the features learned on their intermediate layers.
7 code implementations • 22 Jun 2015 • Jason Yosinski, Jeff Clune, Anh Nguyen, Thomas Fuchs, Hod Lipson
The first is a tool that visualizes the activations produced on each layer of a trained convnet as it processes an image or video (e. g. a live webcam stream).
no code implementations • 23 May 2015 • Henok Mengistu, Joost Huizinga, Jean-Baptiste Mouret, Jeff Clune
Hierarchical organization -- the recursive composition of sub-modules -- is ubiquitous in biological networks, including neural, metabolic, ecological, and genetic regulatory networks, and in human-made systems, such as large organizations and the Internet.
6 code implementations • 20 Apr 2015 • Jean-Baptiste Mouret, Jeff Clune
Interestingly, because MAP-Elites explores more of the search space, it also tends to find a better overall solution than state-of-the-art search algorithms.
2 code implementations • CVPR 2015 • Anh Nguyen, Jason Yosinski, Jeff Clune
Here we show a related result: it is easy to produce images that are completely unrecognizable to humans, but that state-of-the-art DNNs believe to be recognizable objects with 99. 99% confidence (e. g. labeling with certainty that white noise static is a lion).
3 code implementations • NeurIPS 2014 • Jason Yosinski, Jeff Clune, Yoshua Bengio, Hod Lipson
Such first-layer features appear not to be specific to a particular dataset or task, but general in that they are applicable to many datasets and tasks.
2 code implementations • 13 Jul 2014 • Antoine Cully, Jeff Clune, Danesh Tarapore, Jean-Baptiste Mouret
As robots leave the controlled environments of factories to autonomously function in more complex, natural environments, they will have to respond to the inevitable fact that they will become damaged.
no code implementations • 17 Apr 2013 • Nick Cheney, Jeff Clune, Jason Yosinski, Hod Lipson
Interactive evolution has shown the potential to create amazing and complex forms in both 2-D and 3-D settings.
no code implementations • 11 Jul 2012 • Jeff Clune, Jean-Baptiste Mouret, Hod Lipson
A central biological question is how natural organisms are so evolvable (capable of quickly adapting to new environments).