arXiv subjects

Anna V. Kononova

Publications and source records attributed to Anna V. Kononova.

At least 55 records · Page 3Linked to original sources

arXiv2024

Interactive embodied evolution for socially adept Artificial General Creatures

We introduce here the concept of Artificial General Creatures (AGC) which encompasses "robotic or virtual agents with a wide enough range of capabilities to ensure their continued survival". With this in mind, we propose a research line aimed at incrementally building both the technology and the trustworthiness of AGC. The core element in this approach is that trust can only be built over time, through demonstrably mutually beneficial interactions. To this end, we advocate starting from unobtrusive, nonthreatening artificial agents that would explicitly collaborate with humans, similarly to what domestic animals do. By combining multiple research fields, from Evolutionary Robotics to Neuroscience, from Ethics to Human-Machine Interaction, we aim at creating embodied, self-sustaining Artificial General Creatures that would form social and emotional connections with humans. Although they would not be able to play competitive online games or generate poems, we argue that creatures akin to artificial pets would be invaluable stepping stones toward symbiotic Artificial General Intelligence.

cs.NE↗

arXiv2024

Solving Deep Reinforcement Learning Tasks with Evolution Strategies and Linear Policy Networks

Although deep reinforcement learning methods can learn effective policies for challenging problems such as Atari games and robotics tasks, algorithms are complex, and training times are often long. This study investigates how Evolution Strategies perform compared to gradient-based deep reinforcement learning methods. We use Evolution Strategies to optimize the weights of a neural network via neuroevolution, performing direct policy search. We benchmark both deep policy networks and networks consisting of a single linear layer from observations to actions for three gradient-based methods, such as Proximal Policy Optimization. These methods are evaluated against three classical Evolution Strategies and Augmented Random Search, which all use linear policy networks. Our results reveal that Evolution Strategies can find effective linear policies for many reinforcement learning benchmark tasks, unlike deep reinforcement learning methods that can only find successful policies using much larger networks, suggesting that current benchmarks are easier to solve than previously assumed. Interestingly, Evolution Strategies also achieve results comparable to gradient-based deep reinforcement learning algorithms for higher-complexity tasks. Furthermore, we find that by directly accessing the memory state of the game, Evolution Strategies can find successful policies in Atari that outperform the policies found by Deep Q-Learning. Evolution Strategies also outperform Augmented Random Search in most benchmarks, demonstrating superior sample efficiency and robustness in training linear policy networks.

cs.LG↗

arXiv2024

Avoiding Redundant Restarts in Multimodal Global Optimization

Naïve restarts of global optimization solvers when operating on multimodal search landscapes may resemble the Coupon's Collector Problem, with a potential to waste significant function evaluations budget on revisiting the same basins of attractions. In this paper, we assess the degree to which such ``duplicate restarts'' occur on standard multimodal benchmark functions, which defines the \textit{redundancy potential} of each particular landscape. We then propose a repelling mechanism to avoid such wasted restarts with the CMA-ES and investigate its efficacy on test cases with high redundancy potential compared to the standard restart mechanism.

cs.NE↗

arXiv2024

A Deep Dive into Effects of Structural Bias on CMA-ES Performance along Affine Trajectories

To guide the design of better iterative optimisation heuristics, it is imperative to understand how inherent structural biases within algorithm components affect the performance on a wide variety of search landscapes. This study explores the impact of structural bias in the modular Covariance Matrix Adaptation Evolution Strategy (modCMA), focusing on the roles of various modulars within the algorithm. Through an extensive investigation involving 435,456 configurations of modCMA, we identified key modules that significantly influence structural bias of various classes. Our analysis utilized the Deep-BIAS toolbox for structural bias detection and classification, complemented by SHAP analysis for quantifying module contributions. The performance of these configurations was tested on a sequence of affine-recombined functions, maintaining fixed optimum locations while gradually varying the landscape features. Our results demonstrate an interplay between module-induced structural bias and algorithm performance across different landscape characteristics.

cs.NE↗

arXiv2024

Explainable Benchmarking for Iterative Optimization Heuristics

Benchmarking heuristic algorithms is vital to understand under which conditions and on what kind of problems certain algorithms perform well. In most current research into heuristic optimization algorithms, only a very limited number of scenarios, algorithm configurations and hyper-parameter settings are explored, leading to incomplete and often biased insights and results. This paper presents a novel approach we call explainable benchmarking. Introducing the IOH-Xplainer software framework, for analyzing and understanding the performance of various optimization algorithms and the impact of their different components and hyper-parameters. We showcase the framework in the context of two modular optimization frameworks. Through this framework, we examine the impact of different algorithmic components and configurations, offering insights into their performance across diverse scenarios. We provide a systematic method for evaluating and interpreting the behaviour and efficiency of iterative optimization heuristics in a more transparent and comprehensible manner, allowing for better benchmarking and algorithm design.

cs.NE↗

arXiv2024

Large-scale Benchmarking of Metaphor-based Optimization Heuristics

The number of proposed iterative optimization heuristics is growing steadily, and with this growth, there have been many points of discussion within the wider community. One particular criticism that is raised towards many new algorithms is their focus on metaphors used to present the method, rather than emphasizing their potential algorithmic contributions. Several studies into popular metaphor-based algorithms have highlighted these problems, even showcasing algorithms that are functionally equivalent to older existing methods. Unfortunately, this detailed approach is not scalable to the whole set of metaphor-based algorithms. Because of this, we investigate ways in which benchmarking can shed light on these algorithms. To this end, we run a set of 294 algorithm implementations on the BBOB function suite. We investigate how the choice of the budget, the performance measure, or other aspects of experimental design impact the comparison of these algorithms. Our results emphasize why benchmarking is a key step in expanding our understanding of the algorithm space, and what challenges still need to be overcome to fully gauge the potential improvements to the state-of-the-art hiding behind the metaphors.

cs.NE↗

arXiv2024

Impact of spatial transformations on landscape features of CEC2022 basic benchmark problems

When benchmarking optimization heuristics, we need to take care to avoid an algorithm exploiting biases in the construction of the used problems. One way in which this might be done is by providing different versions of each problem but with transformations applied to ensure the algorithms are equipped with mechanisms for successfully tackling a range of problems. In this paper, we investigate several of these problem transformations and show how they influence the low-level landscape features of a set of 5 problems from the CEC2022 benchmark suite. Our results highlight that even relatively small transformations can significantly alter the measured landscape features. This poses a wider question of what properties we want to preserve when creating problem transformations, and how to fairly measure them.

cs.NE↗

arXiv2023

Representation-agnostic distance-driven perturbation for optimizing ill-conditioned problems

Locality is a crucial property for efficiently optimising black-box problems with randomized search heuristics. However, in practical applications, it is not likely to always find such a genotype encoding of candidate solutions that this property is upheld with respect to the Hamming distance. At the same time, it may be possible to use domain-specific knowledge to define a metric with locality property. We propose two mutation operators to solve such optimization problems more efficiently using the metric. The first operator assumes prior knowledge about the distance, the second operator uses the distance as a black box. Those operators apply an estimation of distribution algorithm to find the best mutant according to the defined in the paper function, which employs the given distance. For pseudo-boolean and integer optimization problems, we experimentally show that both mutation operators speed up the search on most of the functions when applied in considered evolutionary algorithms and random local search. Moreover, those operators can be applied in any randomized search heuristic which uses perturbations. However, our mutation operators increase wall-clock time and so are helpful in practice when distance is (much) cheaper to compute than the real objective function.

cs.NE↗

arXiv2023

Analysis of modular CMA-ES on strict box-constrained problems in the SBOX-COST benchmarking suite

Box-constraints limit the domain of decision variables and are common in real-world optimization problems, for example, due to physical, natural or spatial limitations. Consequently, solutions violating a box-constraint may not be evaluable. This assumption is often ignored in the literature, e.g., existing benchmark suites, such as COCO/BBOB, allow the optimizer to evaluate infeasible solutions. This paper presents an initial study on the strict-box-constrained benchmarking suite (SBOX-COST), which is a variant of the well-known BBOB benchmark suite that enforces box-constraints by returning an invalid evaluation value for infeasible solutions. Specifically, we want to understand the performance difference between BBOB and SBOX-COST as a function of two initialization methods and six constraint-handling strategies all tested with modular CMA-ES. We find that, contrary to what may be expected, handling box-constraints by saturation is not always better than not handling them at all. However, across all BBOB functions, saturation is better than not handling, and the difference increases with the number of dimensions. Strictly enforcing box-constraints also has a clear negative effect on the performance of classical CMA-ES (with uniform random initialization and no constraint handling), especially as problem dimensionality increases.

cs.NE↗

arXiv2023

Challenges of ELA-guided Function Evolution using Genetic Programming

Within the optimization community, the question of how to generate new optimization problems has been gaining traction in recent years. Within topics such as instance space analysis (ISA), the generation of new problems can provide new benchmarks which are not yet explored in existing research. Beyond that, this function generation can also be exploited for solving complex real-world optimization problems. By generating functions with similar properties to the target problem, we can create a robust test set for algorithm selection and configuration. However, the generation of functions with specific target properties remains challenging. While features exist to capture low-level landscape properties, they might not always capture the intended high-level features. We show that a genetic programming (GP) approach guided by these exploratory landscape analysis (ELA) properties is not always able to find satisfying functions. Our results suggest that careful considerations of the weighting of landscape properties, as well as the distance measure used, might be required to evolve functions that are sufficiently representative to the target landscape.

cs.NE↗

arXiv2023

Patterns of Convergence and Bound Constraint Violation in Differential Evolution on SBOX-COST Benchmarking Suite

This study investigates the influence of several bound constraint handling methods (BCHMs) on the search process specific to Differential Evolution (DE), with a focus on identifying similarities between BCHMs and grouping patterns with respect to the number of cases when a BCHM is activated. The empirical analysis is conducted on the SBOX-COST benchmarking test suite, where bound constraints are enforced on the problem domain. This analysis provides some insights that might be useful in designing adaptive strategies for handling such constraints.

cs.NE↗

arXiv2023

When to be Discrete: Analyzing Algorithm Performance on Discretized Continuous Problems

The domain of an optimization problem is seen as one of its most important characteristics. In particular, the distinction between continuous and discrete optimization is rather impactful. Based on this, the optimizing algorithm, analyzing method, and more are specified. However, in practice, no problem is ever truly continuous. Whether this is caused by computing limits or more tangible properties of the problem, most variables have a finite resolution. In this work, we use the notion of the resolution of continuous variables to discretize problems from the continuous domain. We explore how the resolution impacts the performance of continuous optimization algorithms. Through a mapping to integer space, we are able to compare these continuous optimizers to discrete algorithms on the exact same problems. We show that the standard $(μ_W, λ)$-CMA-ES fails when discretization is added to the problem.

cs.NE↗

arXiv2023

Modular Differential Evolution

New contributions in the field of iterative optimisation heuristics are often made in an iterative manner. Novel algorithmic ideas are not proposed in isolation, but usually as an extension of a preexisting algorithm. Although these contributions are often compared to the base algorithm, it is challenging to make fair comparisons between larger sets of algorithm variants. This happens because even small changes in the experimental setup, parameter settings, or implementation details can cause results to become incomparable. Modular algorithms offer a way to overcome these challenges. By implementing the algorithmic modifications into a common framework, many algorithm variants can be compared, while ensuring that implementation details match in all versions. In this work, we propose a version of a modular framework for the popular Differential Evolution (DE) algorithm. We show that this modular approach not only aids in comparison, but also allows for a much more detailed exploration of the space of possible DE variants. This is illustrated by showing that tuning the settings of modular DE vastly outperforms a set of commonly used DE versions which have been recreated in our framework. We then investigate these tuned algorithms in detail, highlighting the relation between modules and performance on particular problems.

cs.NE↗

arXiv2023

Deep-BIAS: Detecting Structural Bias using Explainable AI

Evaluating the performance of heuristic optimisation algorithms is essential to determine how well they perform under various conditions. Recently, the BIAS toolbox was introduced as a behaviour benchmark to detect structural bias (SB) in search algorithms. The toolbox can be used to identify biases in existing algorithms, as well as to test for bias in newly developed algorithms. In this article, we introduce a novel and explainable deep-learning expansion of the BIAS toolbox, called Deep-BIAS. Where the original toolbox uses 39 statistical tests and a Random Forest model to predict the existence and type of SB, the Deep-BIAS method uses a trained deep-learning model to immediately detect the strength and type of SB based on the raw performance distributions. Through a series of experiments with a variety of structurally biased scenarios, we demonstrate the effectiveness of Deep-BIAS. We also present the results of using the toolbox on 336 state-of-the-art optimisation algorithms, which showed the presence of various types of structural bias, particularly towards the centre of the objective space or exhibiting discretisation behaviour. The Deep-BIAS method outperforms the BIAS toolbox both in detecting bias and for classifying the type of SB. Furthermore, explanations can be derived using XAI techniques.

cs.NE↗

arXiv2022

Multi-surrogate Assisted Efficient Global Optimization for Discrete Problems

Decades of progress in simulation-based surrogate-assisted optimization and unprecedented growth in computational power have enabled researchers and practitioners to optimize previously intractable complex engineering problems. This paper investigates the possible benefit of a concurrent utilization of multiple simulation-based surrogate models to solve complex discrete optimization problems. To fulfill this, the so-called Self-Adaptive Multi-surrogate Assisted Efficient Global Optimization algorithm (SAMA-DiEGO), which features a two-stage online model management strategy, is proposed and further benchmarked on fifteen binary-encoded combinatorial and fifteen ordinal problems against several state-of-the-art non-surrogate or single surrogate assisted optimization algorithms. Our findings indicate that SAMA-DiEGO can rapidly converge to better solutions on a majority of the test problems, which shows the feasibility and advantage of using multiple surrogate models in optimizing discrete problems.

cs.NE↗

arXiv2022

BBOB Instance Analysis: Landscape Properties and Algorithm Performance across Problem Instances

Benchmarking is a key aspect of research into optimization algorithms, and as such the way in which the most popular benchmark suites are designed implicitly guides some parts of algorithm design. One of these suites is the black-box optimization benchmarking (BBOB) suite of 24 single-objective noiseless functions, which has been a standard for over a decade. Within this problem suite, different instances of a single problem can be created, which is beneficial for testing the stability and invariance of algorithms under transformations. In this paper, we investigate the BBOB instance creation protocol by considering a set of 500 instances for each BBOB problem. Using exploratory landscape analysis, we show that the distribution of landscape features across BBOB instances is highly diverse for a large set of problems. In addition, we run a set of eight algorithms across these 500 instances, and investigate for which cases statistically significant differences in performance occur. We argue that, while the transformations applied in BBOB instances do indeed seem to preserve the high-level properties of the functions, their difference in practice should not be overlooked, particularly when treating the problems as box-constrained instead of unconstrained.

cs.NE↗

arXiv2022

Optimizing Stimulus Energy for Cochlear Implants with a Machine Learning Model of the Auditory Nerve

Performing simulations with a realistic biophysical auditory nerve fiber model can be very time consuming, due to the complex nature of the calculations involved. Here, a surrogate (approximate) model of such an auditory nerve fiber model was developed using machine learning methods, to perform simulations more efficiently. Several machine learning models were compared, of which a Convolutional Neural Network showed the best performance. In fact, the Convolutional Neural Network was able to emulate the behavior of the auditory nerve fiber model with extremely high similarity ($R^2 > 0.99$), tested under a wide range of experimental conditions, whilst reducing the simulation time by five orders of magnitude. In addition, we introduce a method for randomly generating charge-balanced waveforms using hyperplane projection. In the second part of this paper, the Convolutional Neural Network surrogate model was used by an Evolutionary Algorithm to optimize the shape of the stimulus waveform in terms energy efficiency. The resulting waveforms resemble a positive Gaussian-like peak, preceded by an elongated negative phase. When comparing the energy of the waveforms generated by the Evolutionary Algorithm with the commonly used square wave, energy decreases of 8% - 45% were observed for different pulse durations. These results were validated with the original auditory nerve fiber model, which demonstrates that our proposed surrogate model can be used as its accurate and efficient replacement.

q-bio.NC↗

arXiv2022

Deep Multiagent Reinforcement Learning: Challenges and Directions

This paper surveys the field of deep multiagent reinforcement learning. The combination of deep neural networks with reinforcement learning has gained increased traction in recent years and is slowly shifting the focus from single-agent to multiagent environments. Dealing with multiple agents is inherently more complex as (a) the future rewards depend on multiple players' joint actions and (b) the computational complexity increases. We present the most common multiagent problem representations and their main challenges, and identify five research areas that address one or more of these challenges: centralised training and decentralised execution, opponent modelling, communication, efficient coordination, and reward shaping. We find that many computational studies rely on unrealistic assumptions or are not generalisable to other settings; they struggle to overcome the curse of dimensionality or nonstationarity. Approaches from psychology and sociology capture promising relevant behaviours, such as communication and coordination, to help agents achieve better performance in multiagent settings. We suggest that, for multiagent reinforcement learning to be successful, future research should address these challenges with an interdisciplinary approach to open up new possibilities in multiagent reinforcement learning.

cs.LG↗