Jeff Clune

University of British Columbia | UBC · Department of Computer Science

This work identifies a simple pre-training mechanism that leads to representations exhibiting better continual and transfer learning. This mechanism—the repeated resetting of weights in the last layer, which we nickname “zapping”—was originally designed for a meta-continual-learning procedure, yet we show it is surprisingly applicable in many setti...

Researchers are investing substantial effort in developing powerful general-purpose agents, wherein Foundation Models are used as modules within agentic systems (e.g. Chain-of-Thought, Self-Reflection, Toolformer). However, the history of machine learning teaches us that hand-designed solutions are eventually replaced by learned solutions. We formu...

One of the grand challenges of artificial general intelligence is developing agents capable of conducting scientific research and discovering new knowledge. While frontier models have already been used as aids to human scientists, e.g. for brainstorming ideas, writing code, or prediction tasks, they still conduct only a small part of the scientific...

Open-ended and AI-generating algorithms aim to continuously generate and solve increasingly complex tasks indefinitely, offering a promising path toward more general intelligence. To accomplish this grand vision, learning must occur within a vast array of potential tasks. Existing approaches to automatically generating environments are constrained...

Go-Explore is a powerful family of algorithms designed to solve hard-exploration problems, built on the principle of archiving discovered states, and iteratively returning to and exploring from the most promising states. This approach has led to superhuman performance across a wide variety of challenging problems including Atari games and robotic c...

Standard reinforcement learning (RL) agents never intelligently explore like a human (i.e. by taking into account complex domain priors and previous explorations). Even the most basic intelligent exploration strategies such as exhaustive search are only inefficiently or poorly approximated by approaches such as novelty search or intrinsic motivatio...

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 filtering for tasks the current agent can learn (i.e., learning progress), countless learnable yet uninteresting tasks remain (e.g., minor variations of previously learne...

Language is often considered a key aspect of human thinking, providing us with exceptional abilities to generalize, explore, plan, replan, and adapt to new situations. However, Reinforcement Learning (RL) agents are far from human-level performance in any of these abilities. We hypothesize one reason for such cognitive deficiencies is that they lac...

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. However, for many sequential decision domains such as robotics, video games, and computer use, publicly available data does not contain the labels required to train behavi...

An important challenge in reinforcement learning is to solve multimodal problems, where agents have to act in qualitatively different ways depending on the circumstances. Because multimodal problems are often too difficult to solve directly, it is often helpful to define a curriculum, which is an ordered set of subtasks that can serve as the steppi...

Biological organisms learn from interactions with their environment throughout their lifetime. For artificial systems to successfully act and adapt in the real world, it is desirable to similarly be able to learn on a continual basis. This challenge is known as lifelong learning, and remains to a large extent unsolved. In this Perspective article,...

Existing machines are functionally specific tools that were made for easy prediction and control. Tomorrow's machines may be closer to biological systems in their mutability, resilience, and autonomy. But first they must be capable of learning, and retaining, new information without repeated exposure to it. Past efforts to engineer such systems hav...

An important challenge in reinforcement learning is training agents that can solve a wide variety of tasks. If tasks depend on each other (e.g. needing to learn to walk before learning to run), curriculum learning can speed up learning by focusing on the next best task to learn. We explore curriculum learning in a complex, visual domain with many h...

Reinforcement learning promises to solve complex sequential-decision problems autonomously by specifying a high-level reward function only. However, reinforcement learning algorithms struggle when, as is often the case, simple and intuitive rewards provide sparse1 and deceptive2 feedback. Avoiding these pitfalls requires a thorough exploration of t...

A typical camera trap survey may produce millions of images that require slow, expensive manual review. Consequently, critical conservation questions may be answered too slowly to support decision‐making. Recent studies demonstrated the potential for computer vision to dramatically increase efficiency in image‐based biodiversity surveys; however, t...

Motion-activated wildlife cameras (or “camera traps”) are frequently used to remotely and noninvasively observe animals. The vast number of images collected from camera trap projects has prompted some biologists to employ machine learning algorithms to automatically recognize species in these images, or at least filter-out images that do not contai...

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 biological evolution. Recently, interest has grown within the broader field of AI in a generalization of open-ended evolution, here called open-ended search, wherein such...

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. Inspired by how biological motifs such as cells a...

The promise of reinforcement learning is to solve complex sequential decision problems by specifying a high-level reward function only. However, RL algorithms struggle when, as is often the case, simple and intuitive rewards provide sparse and deceptive feedback. Avoiding these pitfalls requires thoroughly exploring the environment, but despite sub...

Recent advances in machine learning are consistently enabled by increasing amounts of computation. Reinforcement learning (RL) and population-based methods in particular pose unique challenges for efficiency and flexibility to the underlying distributed computing frameworks. These challenges include frequent interaction with simulations, the need f...

1. Motion-activated wildlife cameras (or "camera traps") are frequently used to remotely and non-invasively observe animals. The vast number of images collected from camera trap projects have prompted some biologists to employ machine learning algorithms to automatically recognize species in these images, or at least filter-out images that do not c...

Motion-activated wildlife cameras (or “camera traps”) are frequently used to remotely and non-invasively observe animals. The vast number of images collected from camera trap projects have prompted some biologists to employ machine learning algorithms to automatically recognize species in these images, or at least filter-out images that do not cont...

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. A recent step in this direction is the Paired Open-Ended Trailblazer (POET), an algorithm that generates and solves its own challenges, and al...

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. However, present implementations of MAP-Elites and other QD a...

The impressive lifelong learning in animal brains is primarily enabled by plastic changes in synaptic connectivity. Importantly, these changes are not passive, but are actively controlled by neuromodulation, which is itself under the control of the brain. The resulting self-modifying abilities of the brain play an important role in learning and ada...

Continual lifelong learning requires an agent or model to learn many sequentially ordered tasks, building on previous knowledge without catastrophically forgetting it. Much work has gone towards preventing the default tendency of machine learning models to catastrophically forget, yet virtually all such work involves manually-designed solutions to...

Evolution provides a creative fount of complex and subtle adaptations that often surprise the scientists who discover them. However, the creativity of evolution is not limited to the natural world: Artificial organisms evolving in computational environments have also elicited surprise and wonder from the researchers studying them. The process of ev...

This paper investigates the intriguing question of whether we can create learning algorithms that automatically generate training data, learning environments, and curricula in order to help AI agents rapidly learn. We show that such algorithms are possible via Generative Teaching Networks (GTNs), a general approach that is, in theory, applicable to...

Biodiversity conservation depends on accurate, up-to-date information about wildlife population distributions. Motion-activated cameras, also known as camera traps, are a critical tool for population surveys, as they are cheap and non-intrusive. However, extracting useful information from camera trap images is a cumbersome process: a typical camera...

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. Recent advances in machine learning enable a family of methods to synthesize preferred stimuli that cause a neuron in an artificial or biological brain to fire strongly. Those methods are known as A...

Much human and computational effort has aimed to improve how deep reinforcement learning (DRL) algorithms perform on benchmarks such as the Atari Learning Environment. Comparatively less effort has focused on understanding what has been learned by such methods, and investigating and comparing the representations learned by different families of DRL...

Designing evolutionary algorithms capable of uncovering highly evolvable representations is an open challenge in evolutionary computation; such evolvability is important in practice, because it accelerates evolution and enables fast adaptation to changing circumstances. This paper introduces evolvability ES, an evolutionary algorithm designed to ex...

How can progress in machine learning and reinforcement learning be automated to generate its own never-ending curriculum of challenges without human intervention? The recent emergence of quality diversity (QD) algorithms offers a glimpse of the potential for such continual open-ended invention. For example, novelty search showcases the benefits of...

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. This paper introduces evolvability ES, an evolutionary algorithm designed to explicitly and efficiently optimize for evo...

Perhaps the most ambitious scientific quest in human history is the creation of general artificial intelligence, which roughly means AI that is as smart or smarter than humans. The dominant approach in the machine learning community is to attempt to discover each of the pieces required for intelligence, with the implicit assumption that some future...

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. Recent advances in machine learning enable a family of methods to synthesize preferred stimuli that cause a neuron in an artificial or biological brain to fire strongly. Those methods are known as A...

Motion‐activated cameras (“camera traps”) are increasingly used in ecological and management studies for remotely observing wildlife and are amongst the most powerful tools for wildlife research. However, studies involving camera traps result in millions of images that need to be analysed, typically by visually observing each image, in order to ext...

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-exploration domains: Montezuma's Revenge and Pitfall. On both games, current RL algorithms perform poorly, even those with intrinsic motivation, which is the dominant method to im...

Much of recent machine learning has focused on deep learning, in which neural network weights are trained through variants of stochastic gradient descent. An alternative approach comes from the field of neuroevolution, which harnesses evolutionary algorithms to optimize neural networks, inspired by the fact that natural brains themselves are the pr...

While the history of machine learning so far encompasses a series of problems posed by researchers and algorithms that learn their solutions, an important question is whether the problems themselves can be generated by the algorithm at the same time as they are being solved. Such a process would in effect build its own diverse and expanding curricu...

Deep learning provides a powerful tool for machine perception when the observations resemble the training data. However, real-world robotic systems must react intelligently to their observations even in unexpected circumstances. This requires a system to reason about its own uncertainty given unfamiliar, out-of-distribution observations. Approximat...

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 effort has focused on understanding what has been learned by such methods, and investigating and comparing the representations learned by different families of reinforce...

Machine Learning for Wildlife Image Classification (MLWIC) is an R package that allows users to automatically classify animal species in camera trap images. The package comes with a build in model that was trained to recognize 27 North American species using over 3.7 million images. It works rapidly (> 2,000 images/minute on a laptop computer) and...

An important challenge in reinforcement learning, including evolutionary robotics, is to solve multimodal problems, where agents have to act in qualitatively different ways depending on the circumstances. Because multimodal problems are often too difficult to solve directly, it is helpful to take advantage of staging, where a difficult task is divi...

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. However, it remains a challenge to analyze and interpret the underlying process of neuroevolution in su...

While neuroevolution (evolving neural networks) has been successful across a variety of domains from reinforcement learning, to artificial life, to evolutionary robotics, it is rarely applied to large, deep neural networks. A central reason is that while random mutation generally works in low dimensions, a random perturbation of thousands or millio...

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 reinforcement learning domains. It searches for neural network parameters by generating perturbations to the current set of parameters, checking their performance, and mo...

1. Motion-activated cameras (“camera traps”) are increasingly used in ecological and management studies for remotely observing wildlife and have been regarded as among the most powerful tools for wildlife research. However, studies involving camera traps result in millions of images that need to be analyzed, typically by visually observing each ima...

Traditional exploration methods in RL require agents to perform random actions to find rewards. But these approaches struggle on sparse-reward domains like Montezuma's Revenge where the probability that any random action sequence leads to reward is extremely low. Recent algorithms have performed well on such tasks by encouraging agents to visit new...

Traditional exploration methods in reinforcement learning (RL) require agents to perform random actions to find rewards. But these approaches struggle on sparse-reward domains like Montezuma's Revenge where the probability that any random action sequence leads to reward is extremely low. Recent algorithms have performed well on such tasks by encour...

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. However, it remains a challenge to analyze and interpret the underlying process of neuroevolution in su...

How can we build agents that keep learning from experience, quickly and efficiently, after their initial training? Here we take inspiration from the main mechanism of learning in biological brains: synaptic plasticity, carefully tuned by evolution to produce efficient lifelong learning. We show that plasticity, just like connection weights, can be...

Biological evolution provides a creative fount of complex and subtle adaptations, often surprising the scientists who discover them. However, because evolution is an algorithmic process that transcends the substrate in which it occurs, evolution's creativity is not limited to nature. Indeed, many researchers in the field of digital evolution have o...

Biological evolution provides a creative fount of complex and subtle adaptations, often surprising the scientists who discover them. However, because evolution is an algorithmic process that transcends the substrate in which it occurs, evolution's creativity is not limited to nature. Indeed, many researchers in the field of digital evolution have o...

An evolution strategy (ES) variant recently attracted significant attention due to its surprisingly good performance at optimizing neural networks in challenging deep reinforcement learning domains. It searches directly in the parameter space of neural networks by generating perturbations to the current set of parameters, checking their performance...

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. A central reason is that while random mutation generally works in low dimensions, a random perturbation of thousands or millions of weights is...

Deep artificial neural networks (DNNs) are typically trained via gradient-based learning algorithms, namely backpropagation. Evolution strategies (ES) can rival backprop-based algorithms such as Q-learning and policy gradients on challenging deep reinforcement learning (RL) problems. However, ES can be considered a gradient-based algorithm because...

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). For that reason, the recent result from OpenAI showing that a particular kind of evolution strategy (ES) ca...

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. However, many RL problems require directed explo...

A long-term goal of AI is to produce agents that can learn a diversity of skills throughout their lifetimes and continuously improve those skills via experience. A longstanding obstacle towards that goal is catastrophic forgetting, which is when learning new information erases previously learned information. Catastrophic forgetting occurs in artifi...

20 random CFNs for the best and worst PA individuals. Each block contains the unsimplified version of the individual followed by 20 of its CFNs. (TIFF)

Differences between this work and Ellefsen et al. [16]. Differences prevent direct comparison between the non-diffusion treatments in this work and the networks in Ellefsen et al. [16]. Purpose of many of the changes were to make it easier for modular solutions to appear in order to investigate whether they aid with catastrophic forgetting. (TIFF)

20 random CFNs for the best and worst PA_D individuals. Each block contains the unsimplified version of the individual followed by 20 of its CFNs. (TIFF)

20 random CFNs for the best and worst PCC_D individuals. Each block contains the unsimplified version of the individual followed by 20 of its CFNs. (TIFF)

20 random CFNs for the best and worst PCC individuals. Each block contains the unsimplified version of the individual followed by 20 of its CFNs. (TIFF)

Network topology. Individuals in the foraging task are represented as ANNs where each node possesses an (x, y) position. The first three inputs correspond to food items while the last two inputs are fed positive (1) and negative (−1) feedback signals for the summer and winter season respectively. An output greater than 0 results in the agent eating...

Plot of all seasonal associations. See main text for description and interpretation. For further details on seasonal associations see Ellefsen et al. [16]. (TIF)

A 1-connection knockout in the Core Functional Networks (CFNs) confirms that ARK properly identifies functional modules. The original summer and winter fitness for all CFNs is plotted along with the summer and winter fitness after the knockout of a random, common, winter, or summer functional connection. The original (no connection) and random conn...

A long-term goal of AI is to produce agents that can learn a diversity of skills throughout their lifetimes and continuously improve those skills via experience. A longstanding obstacle towards that goal is catastrophic forgetting, which is when learning new information erases previously learned information. Catastrophic forgetting occurs in artifi...

Natural evolution has produced a tremendous diversity of functional organisms. Many believe an essential component of this process was the evolution of evolvability, whereby evolution speeds up its ability to innovate by generating a more adaptive pool of offspring. One hypothesized mechanism for evolvability is developmental canalization, wherein...

Natural evolution has produced a tremendous diversity of functional organisms. Many believe an essential component of this process was the evolution of evolvability, whereby evolution speeds up its ability to innovate by generating a more adaptive pool of offspring. One hypothesized mechanism for evolvability is developmental canalization, wherein...

One of the most intriguing questions in evolution is how organisms exhibit suitable phenotypic variation to rapidly adapt in novel selective environments. Such variability is crucial for evolvability, but poorly understood. In particular, how can natural selection favour developmental organisations that facilitate adaptive evolution in previously u...

Supplementary material. (PDF)

Many challenging engineering problems are regular, meaning solutions to one part of a problem can be reused to solve other parts. Evolutionary algorithms with indirect encoding perform better on regular problems because they reuse genomic information to create regular phenotypes. However, on problems that are mostly regular, but contain some irregu...

Significance Motion-sensor cameras in natural habitats offer the opportunity to inexpensively and unobtrusively gather vast amounts of data on animals in the wild. A key obstacle to harnessing their potential is the great cost of having humans analyze each image. Here, we demonstrate that a cutting-edge type of artificial intelligence called deep n...

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. We investigate the ability to automatically, accurately, and inexpensively collect such data, which could transform many fields of biology, ecology, and zoology into "big data...