This paper surveys the field of deep multiagent reinforcement learning (RL). The combination of deep neural networks with RL 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 RL to be successful, future research should address these challenges with an interdisciplinary approach to open up new possibilities in multiagent RL.

Differential evolution is one of the most prestigious population-based stochastic optimization algorithm for black-box problems. The performance of a differential evolution algorithm depends highly on its mutation and crossover strategy and associated control parameters. However, the determination process for the most suitable parameter setting is troublesome and time consuming. Adaptive control parameter methods that can adapt to problem landscape and optimization environment are more preferable than fixed parameter settings. This article proposes a novel adaptive parameter control approach based on learning from the optimization experiences over a set of problems. In the approach, the parameter control is modeled as a finite-horizon Markov decision process. A reinforcement learning algorithm, named policy gradient, is applied to learn an agent (i.e., parameter controller) that can provide the control parameters of a proposed differential evolution adaptively during the search procedure. The differential evolution algorithm based on the learned agent is compared against nine well-known evolutionary algorithms on the CEC'13 and CEC'17 test suites. Experimental results show that the proposed algorithm performs competitively against these compared algorithms on the test suites.

Automated machine learning (AutoML) is a young research area aiming at making high-performance machine learning techniques accessible to a broad set of users. This is achieved by identifying all design choices in creating a machine-learning model and addressing them automatically to generate performance-optimised models. In this article, we provide an extensive overview of the past and present, as well as future perspectives of AutoML. First, we introduce the concept of AutoML, formally define the problems it aims to solve and describe the three components underlying AutoML approaches: the search space, search strategy and performance evaluation. Next, we discuss hyperparameter optimisation (HPO) techniques commonly used in AutoML systems design, followed by providing an overview of the neural architecture search, a particular case of AutoML for automatically generating deep learning models. We further review and compare available AutoML systems. Finally, we provide a list of open challenges and future research directions. Overall, we offer a comprehensive overview for researchers and practitioners in the area of machine learning and provide a basis for further developments in AutoML.

Large Language Models (LLMs) such as GPT-4 have demonstrated their ability to understand natural language and generate complex code snippets. This paper introduces a novel Large Language Model Evolutionary Algorithm (LLaMEA) framework, leveraging GPT models for the automated generation and refinement of algorithms. Given a set of criteria and a task definition (the search space), LLaMEA iteratively generates, mutates and selects algorithms based on performance metrics and feedback from runtime evaluations. This framework offers a unique approach to generating optimized algorithms without requiring extensive prior expertise. We show how this framework can be used to generate novel black-box metaheuristic optimization algorithms for box-constrained, continuous optimization problems automatically. LLaMEA generates multiple algorithms that outperform state-of-the-art optimization algorithms (Covariance Matrix Adaptation Evolution Strategy and Differential Evolution) on the 5-dimensional black box optimization benchmark (BBOB). The algorithms also show competitive performance on the 10-and 20-dimensional instances of the test functions, although they have not seen such instances during the automated generation process. The results demonstrate the feasibility of the framework and identify future directions for automated generation and optimization of algorithms via LLMs.