Improvisation--the art of spontaneous creation that unfolds moment-to-moment without a scripted outcome--requires practitioners to continuously sense, adapt, and create anew. It is a fundamental mode of human creativity spanning music, dance, and everyday life. The open-ended nature of improvisation produces a stream of novel, unrepeatable moments--an aspect highly valued in artistic creativity. In parallel, open-endedness (OE)--a system's capacity for unbounded novelty and endless "interestingness"--is exemplified in natural or cultural evolution and has been considered "the last grand challenge" in artificial life (ALife). The rise of generative AI now raises the question in computational creativity (CC) research: What makes a "good" improvisation for AI? Can AI learn to improvise in a genuinely open-ended way? In this work-in-progress paper, we report insights from in-depth interviews with 6 experts in improvisation across dance, music, and contact improvisation. We draw systemic connections between human improvisa-tional arts and the design of future experiential AI agents that could improvise alone or alongside humans--or even with other AI agents--embodying qualities of improvisation drawn from practice: active listening (umwelt and awareness), being in the time (mindfulness and ephemerality), embracing the unknown (source of randomness and serendipity), non-judgmental flow (acceptance and dynamical stability, balancing structure and surprise (unpredictable criticality at edge of chaos), imaginative metaphor (synaesthesia and planning), empathy, trust, boundary, and care (mutual theory of mind), and playfulness and intrinsic motivation (maintaining interestingness).

Artificial Life (ALife) as an interdisciplinary field draws inspiration and influence from a variety of perspectives. Scientific progress crucially depends, then, on concerted efforts to invite cross-disciplinary dialogue. The goal of this paper is to revitalize discussions of potential connections between the fields of Computational Creativity (CC) and ALife, focusing specifically on the concept of Open-Endedness (OE); the primary goal of CC is to endow artificial systems with creativity, and ALife has dedicated much research effort into studying and synthesizing OE and artificial innovation. However, despite the close proximity of these concepts, their use so far remains confined to their respective communities, and their relationship is largely unclear. We provide historical context for research in both domains, and review the limited work connecting research on creativity and OE explicitly. We then highlight specific questions to be considered, with the eventual goals of (i) decreasing conceptual ambiguity by highlighting similarities and differences between the concepts of OE and creativity, (ii) identifying synergy effects of a research agenda that encompasses both concepts, and (iii) establishing a dialogue between ALife and CC research.

In recent years there has been a tremendous surge in the general capabilities of AI systems, mainly fuelled by training foundation models on internetscale data. Nevertheless, the creation of openended, ever self-improving AI remains elusive. In this position paper, we argue that the ingredients are now in place to achieve openendedness in AI systems with respect to a human observer. Furthermore, we claim that such open-endedness is an essential property of any artificial superhuman intelligence (ASI). We begin by providing a concrete formal definition of open-endedness through the lens of novelty and learnability. We then illustrate a path towards ASI via open-ended systems built on top of foundation models, capable of making novel, humanrelevant discoveries. We conclude by examining the safety implications of generally-capable openended AI. We expect that open-ended foundation models will prove to be an increasingly fertile and safety-critical area of research in the near future.

Reinforcement Learning from Human Feedback (RLHF) has shown potential in qualitative tasks where clear objectives are lacking. However, its effectiveness is not fully realized when it is conceptualized merely as a tool to optimize average human preferences, especially in generative tasks that demand diverse model responses. Meanwhile, Quality Diversity (QD) algorithms excel at identifying diverse and high-quality solutions but often rely on manually crafted diversity metrics. This paper introduces Quality Diversity through Human Feedback (QDHF), a novel approach integrating human feedback into the QD framework. QDHF infers diversity metrics from human judgments of similarity among solutions, thereby enhancing the applicability and effectiveness of QD algorithms. Our empirical studies show that QDHF significantly outperforms state-of-the-art methods in automatic diversity discovery and matches the efficacy of using manually crafted metrics for QD on standard benchmarks in robotics and reinforcement learning. Notably, in a latent space illumination task, QDHF substantially enhances the diversity in images generated by a diffusion model and was more favorably received in user studies. We conclude by analyzing QDHF's scalability and the quality of its derived diversity metrics, emphasizing its potential to improve exploration and diversity in complex, open-ended optimization tasks. Source code is available on GitHub: https://github.com/ld-ing/qdhf.

Diversity plays a significant role in many problems, such as ensemble learning, reinforcement learning, and combinatorial optimization. How to define the diversity measure is a longstanding problem. Many methods rely on expert experience to define a proper behavior space and then obtain the diversity measure, which is, however, challenging in many scenarios. In this paper, we propose the problem of learning a behavior space from human feedback and present a general method called Diversity from Human Feedback (DivHF) to solve it. DivHF learns a behavior descriptor consistent with human preference by querying human feedback. The learned behavior descriptor can be combined with any distance measure to define a diversity measure. We demonstrate the effectiveness of DivHF by integrating it with the Quality-Diversity optimization algorithm MAP-Elites and conducting experiments on the QDax suite. The results show that DivHF learns a behavior space that aligns better with human requirements compared to direct data-driven approaches and leads to more diverse solutions under human preference. Our contributions include formulating the problem, proposing the DivHF method, and demonstrating its effectiveness through experiments.

Exploration bonuses in reinforcement learning guide long-horizon exploration by defining custom intrinsic objectives. Several exploration objectives like count-based bonuses, pseudo-counts, and state-entropy maximization are non-stationary and hence are difficult to optimize for the agent. While this issue is generally known, it is usually omitted and solutions remain under-explored. The key contribution of our work lies in transforming the original non-stationary rewards into stationary rewards through an augmented state representation. For this purpose, we introduce the Stationary Objectives For Exploration (SOFE) framework. SOFE requires identifying sufficient statistics for different exploration bonuses and finding an efficient encoding of these statistics to use as input to a deep network. SOFE is based on proposing state augmentations that expand the state space but hold the promise of simplifying the optimization of the agent's objective. We show that SOFE improves the performance of several exploration objectives, including count-based bonuses, pseudo-counts, and state-entropy maximization. Moreover, SOFE outperforms prior methods that attempt to stabilize the optimization of intrinsic objectives. We demonstrate the efficacy of SOFE in hard-exploration problems, including sparse-reward tasks, pixel-based observations, 3D navigation, and procedurally generated environments.

Can we build an artificial system that would be able to generate endless surprises if ran "forever" in Minecraft? While there is not a single path toward solving that grand challenge, this article presents what we believe to be some working ingredients for the endless generation of novel increasingly complex artifacts in Minecraft. Our framework for an open-ended system includes two components: a complex system used to recursively grow and complexify artifacts over time, and a discovery algorithm that leverages the concept of meta-diversity search. Since complex systems have shown to enable the emergence of considerable complexity from set of simple rules, we believe them to be great candidates to generate all sort of artifacts in Minecraft. Yet, the space of possible artifacts that can be generated by these systems is often unknown, challenging to characterize and explore. Therefore automating the long-term discovery of novel and increasingly complex artifacts in these systems is an exciting research field. To approach these challenges, we formulate the problem of meta-diversity search where an artificial "discovery assistant" incrementally learns a diverse set of representations to characterize behaviors and searches to discover diverse patterns within each of them. A successful discovery assistant should continuously seek for novel sources of diversities while being able to quickly specialize the search toward a new unknown type of diversity. To implement those ideas in the Minecraft environment, we simulate an artificial "chemistry" system based on Lenia continuous cellular automaton for generating artifacts, as well as an artificial "discovery assistant" (called Holmes) for the artifact-discovery process. Holmes incrementally learns a hierarchy of modular representations to characterize divergent sources of diversity and uses a goal-based intrinsically-motivated exploration as the diversity search strategy.

This work investigates how a predator-prey scenario can induce the emergence of Open-Ended Evolution (OEE). We utilize modular robots of fixed morphologies whose controllers are subject to evolution. In both species, robots can send and receive signals and perceive the relative positions of other robots in the environment. Specifically, we introduce a feature we call a tagging system: it modifies how individuals can perceive each other and is expected to increase behavioral complexity. Our results show the emergence of adaptive strategies, demonstrating the viability of inducing OEE through predator-prey dynamics using modular robots. Such emergence, nevertheless, seemed to depend on conditioning reproduction to an explicit behavioral criterion.

Modern artificial intelligence works typically train the parameters of fixed-sized deep neural networks using gradient-based optimization techniques. Simple evolutionary algorithms have recently been shown to also be capable of optimizing deep neural network parameters, at times matching the performance of gradient-based techniques, e.g. in reinforcement learning settings. In addition to optimizing network parameters, many evolutionary computation techniques are also capable of progressively constructing network architectures. However, constructing network architectures from elementary evolution rules has not yet been shown to scale to modern reinforcement learning benchmarks. In this paper we therefore propose a new approach in which the architectures of recurrent neural networks dynamically evolve according to a small set of mutation rules. We implement a massively parallel evolutionary algorithm and run experiments on all 19 OpenAI Gym state-based reinforcement learning control tasks. We find that in most cases, dynamic agents match or exceed the performance of gradient-based agents while utilizing orders of magnitude fewer parameters. We believe our work to open avenues for real-life applications where network compactness and autonomous design are of critical importance. We provide our source code, final model checkpoints and full results at github.com/MaximilienLC/nra.

Improving open-ended learning capabilities is a promising approach to enable robots to face the unbounded complexity of the real-world. Among existing methods, the ability of Quality-Diversity algorithms to generate large collections of diverse and high-performing skills is instrumental in this context. However, most of those algorithms rely on a hand-coded behavioural descriptor to characterise the diversity, hence requiring prior knowledge about the considered tasks. In this work, we propose an additional analysis of Autonomous Robots Realising their Abilities; a Quality-Diversity algorithm that autonomously finds behavioural characterisations. We evaluate this approach on a simulated robotic environment, where the robot has to autonomously discover its abilities from its full-state trajectories. All algorithms were applied to three tasks: navigation, moving forward with a high velocity, and performing half-rolls. The experimental results show that the algorithm under study discovers autonomously collections of solutions that are diverse with respect to all tasks. More specifically, the analysed approach autonomously finds policies that make the robot move to diverse positions, but also utilise its legs in diverse ways, and even perform half-rolls.