544 citations · 1.7k across the 27 of their papers we have counts for
29 papers
AI Finds A Way
Aaron Dharna, Cong Lu, Ryan Sullivan +3
Artificial Intelligence (AI) algorithms frequently learn creative and unexpected solutions, surprising even expert researchers who develop and study them. They often astonish pract…
Evolution and The Knightian Blindspot of Machine Learning
Joel Lehman, Elliot Meyerson, Tarek El-Gaaly +2
This paper claims that machine learning (ML) largely overlooks an important facet of general intelligence: robustness to a qualitatively unknown future in an open world. Such robus…
OMNI: Open-endedness via Models of human Notions of Interestingness
Jenny Zhang, Joel Lehman, Kenneth Stanley +1
Open-ended algorithms aim to learn new, interesting behaviors forever. That requires a vast environment search space, but there are thus infinitely many possible tasks. Even after…
Machine Love
Joel Lehman
While ML generates much economic value, many of us have problematic relationships with social media and other ML-powered applications. One reason is that ML often optimizes for wha…
Language Model Crossover: Variation through Few-Shot Prompting
Elliot Meyerson, Mark J. Nelson, Herbie Bradley +4
This paper pursues the insight that language models naturally enable an intelligent variation operator similar in spirit to evolutionary crossover. In particular, language models o…
Evolution through Large Models
Joel Lehman, Jonathan Gordon, Shawn Jain +3
This paper pursues the insight that large language models (LLMs) trained to generate code can vastly improve the effectiveness of mutation operators applied to programs in genetic…
Ideas for Improving the Field of Machine Learning: Summarizing Discussion from the NeurIPS 2019 Retrospectives Workshop
Shagun Sodhani, Mayoore S. Jaiswal, Lauren Baker +5
This report documents ideas for improving the field of machine learning, which arose from discussions at the ML Retrospectives workshop at NeurIPS 2019. The goal of the report is t…
Open Questions in Creating Safe Open-ended AI: Tensions Between Control and Creativity
Adrien Ecoffet, Jeff Clune, Joel Lehman
Artificial life originated and has long studied the topic of open-ended evolution, which seeks the principles underlying artificial systems that innovate continually, inspired by b…
Reinforcement Learning Under Moral Uncertainty
Adrien Ecoffet, Joel Lehman
An ambitious goal for machine learning is to create agents that behave ethically: The capacity to abide by human moral norms would greatly expand the context in which autonomous ag…
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…
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…
First return, then explore
Adrien Ecoffet, Joost Huizinga, Joel Lehman +2
The promise of reinforcement learning is to solve complex sequential decision problems autonomously by specifying a high-level reward function only. However, reinforcement learning…
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…
Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data
Felipe Petroski Such, Aditya Rawal, Joel Lehman +2
This paper investigates the intriguing question of whether we can create learning algorithms that automatically generate training data, learning environments, and curricula in orde…
Evolvability ES: Scalable and Direct Optimization of Evolvability
Alexander Gajewski, Jeff Clune, Kenneth O. Stanley +1
Designing evolutionary algorithms capable of uncovering highly evolvable representations is an open challenge; such evolvability is important because it accelerates evolution and e…
Towards Empathic Deep Q-Learning
Bart Bussmann, Jacqueline Heinerman, Joel Lehman
As reinforcement learning (RL) scales to solve increasingly complex tasks, interest continues to grow in the fields of AI safety and machine ethics. As a contribution to these fiel…
Learning Belief Representations for Imitation Learning in POMDPs
Tanmay Gangwani, Joel Lehman, Qiang Liu +1
We consider the problem of imitation learning from expert demonstrations in partially observable Markov decision processes (POMDPs). Belief representations, which characterize the…
Evolutionary Computation and AI Safety: Research Problems Impeding Routine and Safe Real-world Application of Evolution
Joel Lehman
Recent developments in artificial intelligence and machine learning have spurred interest in the growing field of AI safety, which studies how to prevent human-harming accidents wh…
Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
Rui Wang, Joel Lehman, Jeff Clune +1
While the history of machine learning so far largely encompasses a series of problems posed by researchers and algorithms that learn their solutions, an important question is wheth…
Go-Explore: a New Approach for Hard-Exploration Problems
Adrien Ecoffet, Joost Huizinga, Joel Lehman +2
A grand challenge in reinforcement learning is intelligent exploration, especially when rewards are sparse or deceptive. Two Atari games serve as benchmarks for such hard-explorati…
An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents
Felipe Petroski Such, Vashisht Madhavan, Rosanne Liu +8
Much human and computational effort has aimed to improve how deep reinforcement learning algorithms perform on benchmarks such as the Atari Learning Environment. Comparatively less…
An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution
Rosanne Liu, Joel Lehman, Piero Molino +4
Few ideas have enjoyed as large an impact on deep learning as convolution. For any problem involving pixels or spatial representations, common intuition holds that convolutional ne…
The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities
Joel Lehman, Jeff Clune, Dusan Misevic +50
Biological evolution provides a creative fount of complex and subtle adaptations, often surprising the scientists who discover them. However, because evolution is an algorithmic pr…
ES Is More Than Just a Traditional Finite-Difference Approximator
Joel Lehman, Jay Chen, Jeff Clune +1
An evolution strategy (ES) variant based on a simplification of a natural evolution strategy recently attracted attention because it performs surprisingly well in challenging deep…