Search

In biological evolution complex neural structures grow from a handful of cellular ingredients. As genomes in nature are bounded in size, this complexity is achieved by a growth process where cells communicate locally to decide whether to differentiate, proliferate and connect with other cells. This self-organisation is hypothesized to play an important part in the generalisation, and robustness of biological neural networks. Artificial neural networks (ANNs), on the other hand, are traditionally optimized in the space of weights. Thus, the benefits and challenges of growing artificial neural networks remain understudied. Building on the previously introduced Neural Developmental Programs (NDP), in this work we present an algorithm for growing ANNs that solve reinforcement learning tasks. We identify a key challenge: ensuring phenotypic complexity requires maintaining neuronal diversity, but this diversity comes at the cost of optimization stability. To address this, we introduce two mechanisms: (a) equipping neurons with an intrinsic state inherited upon neurogenesis; (b) lateral inhibition, a mechanism inspired by biological growth, which controlls the pace of growth, helping diversity persist. We show that both mechanisms contribute to neuronal diversity and that, equipped with them, NDPs achieve comparable results to existing direct and developmental encodings in complex locomotion tasks

Artificial neural networks used for reinforcement learning are structurally rigid, meaning that each optimized parameter of the network is tied to its specific placement in the network structure. It also means that a network only works with pre-defined and fixed input- and output sizes. This is a consequence of having the number of optimized parameters being directly dependent on the structure of the network. Structural rigidity limits the ability to optimize parameters of policies across multiple environments that do not share input and output spaces. Here, we evolve a set of neurons and plastic synapses each represented by a gated recurrent unit (GRU). During optimization, the parameters of these fundamental units of a neural network are optimized in different random structural configurations. Earlier work has shown that parameter sharing between units is important for making structurally flexible neurons We show that it is possible to optimize a set of distinct neuron- and synapse types allowing for a mitigation of the symmetry dilemma. We demonstrate this by optimizing a single set of neurons and synapses to solve multiple reinforcement learning control tasks simultaneously.

The term “resilience” has risen in popularity following a series of natural disasters, the impacts of climate change, and the Covid-19 pandemic. However, different disciplines use the term in widely different ways, resulting in confusion regarding how the term is used and difficulties operationalising the underlying concept. Drawing on an overview of eleven disciplines, our paper offers a guiding framework to navigate this ambiguity by suggesting a novel typology of resilience using an information-theoretic approach. Specifically, we define resilience by borrowing an existing definition of individuals as sub-systems within multi-scale systems that exhibit temporal integrity amidst interactions with the environment. We quantify resilience as the ability of individuals to maintain fitness in the face of endogenous and exogenous disturbances. In particular, we distinguish between four different types of resilience: (i) preservation of structure and function, which we call “strong robustness”; (ii) preservation of function but change in structure (“weak robustness”); (iii) change in both structure and function (“strong adaptability”); and (iv) change in function but preservation in structure (“weak adaptability”). Our typology offers an approach for navigating these different types and demonstrates how resilience can be operationalised across disciplines.

Neuroevolution (NE) has recently proven a competitive alternative to learning by gradient descent in reinforcement learning tasks. However, the majority of NE methods and associated simulation environments differ crucially from biological evolution: the environment is reset to initial conditions at the end of each generation, whereas natural environments are continuously modified by their inhabitants; agents reproduce based on their ability to maximize rewards within a population, while biological organisms reproduce and die based on internal physiological variables that depend on their resource consumption; simulation environments are primarily single-agent while the biological world is inherently multi-agent and evolves alongside the population. In this work we present a method for continuously evolving adaptive agents without any environment or population reset. The environment is a large grid world with complex spatiotemporal resource generation, containing many agents that are each controlled by an evolvable recurrent neural network and locally reproduce based on their internal physiology. The entire system is implemented in JAX, allowing very fast simulation on a GPU. We show that NE can operate in an ecologically-valid non-episodic multi-agent setting, finding sustainable collective foraging strategies in the presence of a complex interplay between ecological and evolutionary dynamics.

In both natural and artificial studies, evolution is often seen as synonymous to natural selection. Individuals evolve under pressures set by environments that are either reset or do not carry over significant changes from previous generations. Thus, niche construction (NC), the reciprocal process to natural selection where individuals incur inheritable changes to their environment, is ignored. Arguably due to this lack of study, the dynamics of NC are today little understood, especially in real-world settings. In this work, we study NC in simulation environments that consist of multiple, diverse niches and populations that evolve their plasticity, evolvability and niche-constructing behaviors. Our empirical analysis reveals many interesting dynamics, with populations experiencing mass extinctions, arms races and oscillations. To understand these behaviors, we analyze the interaction between NC and adaptability and the effect of NC on the population's genomic diversity and dispersal, observing that NC diversifies niches. Our study suggests that complexifying the simulation environments studying NC, by considering multiple and diverse niches, is necessary for understanding its dynamics and can lend testable hypotheses to future studies of both natural and artificial systems.

Animals often demonstrate a remarkable ability to adapt to their environments during their lifetime. They do so partly due to the evolution of morphological and neural structures. These structures capture features of environments shared between generations to bias and speed up lifetime learning. In this work, we propose a computational model for studying a mechanism that can enable such a process. We adopt a computational framework based on meta reinforcement learning as a model of the interplay between evolution and development. At the evolutionary scale, we evolve reservoirs, a family of recurrent neural networks that differ from conventional networks in that one optimizes not the synaptic weights, but hyperparameters controlling macro-level properties of the resulting network architecture. At the developmental scale, we employ these evolved reservoirs to facilitate the learning of a behavioral policy through Reinforcement Learning (RL). Within an RL agent, a reservoir encodes the environment state before providing it to an action policy. We evaluate our approach on several 2D and 3D simulated environments. Our results show that the evolution of reservoirs can improve the learning of diverse challenging tasks. We study in particular three hypotheses: the use of an architecture combining reservoirs and reinforcement learning could enable (1) solving tasks with partial observability, (2) generating oscillatory dynamics that facilitate the learning of locomotion tasks, and (3) facilitating the generalization of learned behaviors to new tasks unknown during the evolution phase.

Recent works have proven that intricate cooperative behaviors can emerge in agents trained using meta reinforcement learning on open ended task distributions using self-play. While the results are impressive, we argue that self-play and other centralized training techniques do not accurately reflect how general collective exploration strategies emerge in the natural world: through decentralized training and over an open-ended distribution of tasks. In this work we therefore investigate the emergence of collective exploration strategies, where several agents meta-learn independent recurrent policies on an open ended distribution of tasks. To this end we introduce a novel environment with an open ended procedurally generated task space which dynamically combines multiple subtasks sampled from five diverse task types to form a vast distribution of task trees. We show that decentralized agents trained in our environment exhibit strong generalization abilities when confronted with novel objects at test time. Additionally, despite never being forced to cooperate during training the agents learn collective exploration strategies which allow them to solve novel tasks never encountered during training. We further find that the agents learned collective exploration strategies extend to an open ended task setting, allowing them to solve task trees of twice the depth compared to the ones seen during training. Our open source code as well as videos of the agents can be found on our companion website., Comment: Published at the 2nd Agent Learning in Open-Endedness Workshop at NeurIPS 2023

In the intrinsically motivated skills acquisition problem, the agent is set in an environment without any pre-defined goals and needs to acquire an open-ended repertoire of skills. To do so the agent needs to be autotelic (deriving from the Greek auto (self) and telos (end goal)): it needs to generate goals and learn to achieve them following its own intrinsic motivation rather than external supervision. Autotelic agents have so far been considered in isolation. But many applications of open-ended learning entail groups of agents. Multi-agent environments pose an additional challenge for autotelic agents: to discover and master goals that require cooperation agents must pursue them simultaneously, but they have low chances of doing so if they sample them independently. In this work, we propose a new learning paradigm for modeling such settings, the Decentralized Intrinsically Motivated Skills Acquisition Problem (Dec-IMSAP), and employ it to solve cooperative navigation tasks. First, we show that agents setting their goals independently fail to master the full diversity of goals. Then, we show that a sufficient condition for achieving this is to ensure that a group aligns its goals, i.e., the agents pursue the same cooperative goal. Our empirical analysis shows that alignment enables specialization, an efficient strategy for cooperation. Finally, we introduce the Goal-coordination game, a fully-decentralized emergent communication algorithm, where goal alignment emerges from the maximization of individual rewards in multi-goal cooperative environments and show that it is able to reach equal performance to a centralized training baseline that guarantees aligned goals. To our knowledge, this is the first contribution addressing the problem of intrinsically motivated multi-agent goal exploration in a decentralized training paradigm.

The diversity and quality of natural systems have been a puzzle and inspiration for communities studying artificial life. It is now widely admitted that the adaptation mechanisms enabling these properties are largely influenced by the environments they inhabit. Organisms facing environmental variability have two alternative adaptation mechanisms operating at different timescales: \textit{plasticity}, the ability of a phenotype to survive in diverse environments and \textit{evolvability}, the ability to adapt through mutations. Although vital under environmental variability, both mechanisms are associated with fitness costs hypothesized to render them unnecessary in stable environments. In this work, we study the interplay between environmental dynamics and adaptation in a minimal model of the evolution of plasticity and evolvability. We experiment with different types of environments characterized by the presence of niches and a climate function that determines the fitness landscape. We empirically show that environmental dynamics affect plasticity and evolvability differently and that the presence of diverse ecological niches favors adaptability even in stable environments. We perform ablation studies of the selection mechanisms to separate the role of fitness-based selection and niche-limited competition. Results obtained from our minimal model allow us to propose promising research directions in the study of open-endedness in biological and artificial systems.

Human culture relies on innovation: our ability to continuously explore how existing elements can be combined to create new ones. Innovation is not solitary, it relies on collective search and accumulation. Reinforcement learning (RL) approaches commonly assume that fully-connected groups are best suited for innovation. However, human laboratory and field studies have shown that hierarchical innovation is more robustly achieved by dynamic social network structures. In dynamic settings, humans oscillate between innovating individually or in small clusters, and then sharing outcomes with others. To our knowledge, the role of social network structure on innovation has not been systematically studied in RL. Here, we use a multi-level problem setting (WordCraft), with three different innovation tasks to test the hypothesis that the social network structure affects the performance of distributed RL algorithms. We systematically design networks of DQNs sharing experiences from their replay buffers in varying structures (fully-connected, small world, dynamic, ring) and introduce a set of behavioral and mnemonic metrics that extend the classical reward-focused evaluation framework of RL. Comparing the level of innovation achieved by different social network structures across different tasks shows that, first, consistent with human findings, experience sharing within a dynamic structure achieves the highest level of innovation in tasks with a deceptive nature and large search spaces. Second, experience sharing is not as helpful when there is a single clear path to innovation. Third, the metrics we propose, can help understand the success of different social network structures on different tasks, with the diversity of experiences on an individual and group level lending crucial insights.

Despite its rise as a prominent solution to the data inefficiency of today's machine learning models, self-supervised learning has yet to be studied from a purely multi-agent perspective. In this work, we propose that aligning internal subjective representations, which naturally arise in a multi-agent setup where agents receive partial observations of the same underlying environmental state, can lead to more data-efficient representations. We propose that multi-agent environments, where agents do not have access to the observations of others but can communicate within a limited range, guarantees a common context that can be leveraged in individual representation learning. The reason is that subjective observations necessarily refer to the same subset of the underlying environmental states and that communication about these states can freely offer a supervised signal. To highlight the importance of communication, we refer to our setting as \textit{socially supervised representation learning}. We present a minimal architecture comprised of a population of autoencoders, where we define loss functions, capturing different aspects of effective communication, and examine their effect on the learned representations. We show that our proposed architecture allows the emergence of aligned representations. The subjectivity introduced by presenting agents with distinct perspectives of the environment state contributes to learning abstract representations that outperform those learned by a single autoencoder and a population of autoencoders, presented with identical perspectives of the environment state. Altogether, our results demonstrate how communication from subjective perspectives can lead to the acquisition of more abstract representations in multi-agent systems, opening promising perspectives for future research at the intersection of representation learning and emergent communication.

In this paper, we model Density Evolution (DE) using Recurrent Neural Networks (RNNs) with the aim of designing capacity-approaching Irregular Low-Density Parity-Check (LDPC) codes for binary erasure channels. In particular, we present a method for determining the coefficients of the degree distributions, characterizing the structure of an LDPC code. We refer to our RNN architecture as Neural Density Evolution (NDE) and determine the weights of the RNN that correspond to optimal designs by minimizing a loss function that enforces the properties of asymptotically optimal design, as well as the desired structural characteristics of the code. This renders the LDPC design process highly configurable, as constraints can be added to meet applications' requirements by means of modifying the loss function. In order to train the RNN, we generate data corresponding to the expected channel noise. We analyze the complexity and optimality of NDE theoretically, and compare it with traditional design methods that employ differential evolution. Simulations illustrate that NDE improves upon differential evolution both in terms of asymptotic performance and complexity. Although we focus on asymptotic settings, we evaluate designs found by NDE for finite codeword lengths and observe that performance remains satisfactory across a variety of channels.

Recent advances in Artificial Intelligence (AI) have revived the quest for agents able to acquire an open-ended repertoire of skills. However, although this ability is fundamentally related to the characteristics of human intelligence, research in this field rarely considers the processes that may have guided the emergence of complex cognitive capacities during the evolution of the species. Research in Human Behavioral Ecology (HBE) seeks to understand how the behaviors characterizing human nature can be conceived as adaptive responses to major changes in the structure of our ecological niche. In this paper, we propose a framework highlighting the role of environmental complexity in open-ended skill acquisition, grounded in major hypotheses from HBE and recent contributions in Reinforcement learning (RL). We use this framework to highlight fundamental links between the two disciplines, as well as to identify feedback loops that bootstrap ecological complexity and create promising research directions for AI researchers.

In this paper, we propose a novel decentralized framework for optimizing the transmission strategy of Irregular Repetition Slotted ALOHA (IRSA) protocol in sensor networks. We consider a hierarchical communication framework that ensures adaptivity to changing network conditions and does not require centralized control. The proposed solution is inspired by the reinforcement learning literature, and, in particular, Q-learning. To deal with sensor nodes' limited lifetime and communication range, we allow them to decide how many packet replicas to transmit considering only their own buffer state. We show that this information is sufficient and can help avoiding packets' collisions and improving the throughput significantly. We solve the problem using the decentralized partially observable Markov Decision Process (Dec-POMDP) framework, where we allow each node to decide independently of the others how many packet replicas to transmit. We enhance the proposed Q-learning based method with the concept of virtual experience, and we theoretically and experimentally prove that convergence time is, thus, significantly reduced. The experiments prove that our method leads to large throughput gains, in particular when network traffic is heavy, and scales well with the size of the network. To comprehend the effect of the problem's nature on the learning dynamics and vice versa, we investigate the waterfall effect, a severe degradation in performance above a particular traffic load, typical for codes-on-graphs and prove that our algorithm learns to alleviate it.