As the field of multi-agent reinforcement learning (MARL) progresses towards larger and more complex environments, achieving strong performance while maintaining memory efficiency and scalability to many agents becomes increasingly important. Although recent research has led to several advanced algorithms, to date, none fully address all of these key properties simultaneously. In this work, we introduce Sable, a novel and theoretically sound algorithm that adapts the retention mechanism from Retentive Networks to MARL. Sable's retention-based sequence modelling architecture allows for computationally efficient scaling to a large number of agents, as well as maintaining a long temporal context, making it well-suited for large-scale partially observable environments. Through extensive evaluations across six diverse environments, we demonstrate how Sable is able to significantly outperform existing state-of-the-art methods in the majority of tasks (34 out of 45, roughly 75%). Furthermore, Sable demonstrates stable performance as we scale the number of agents, handling environments with more than a thousand agents while exhibiting a linear increase in memory usage. Finally, we conduct ablation studies to isolate the source of Sable's performance gains and confirm its efficient computational memory usage. Our results highlight Sable's performance and efficiency, positioning it as a leading approach to MARL at scale. When considering large-scale practical applications of multi-agent reinforcement learning (MARL) such as autonomous driving (Lian & Deshmukh, 2006; Zhou et al., 2021; Li et al., 2022) and electricity grid control (Kamboj et al., 2011; Li et al., 2016), it becomes increasingly important to maintain three key properties for a system to be effective: strong performance, memory efficiency, and scalability to many agents. Although many existing MARL approaches exhibit one or two of these properties, a solution effectively encompassing all three remains elusive. To briefly illustrate our point, we consider the spectrum of approaches to MARL. Such algorithms demonstrate proficiency in handling many agents in a memory efficient way by typically using shared parameters and conditioning on an agent identifier. However, at scale, the performance of fully decentralised methods remains suboptimal compared to more centralised approaches (Papoudakis et al., 2021; Yu et al., 2022; Wen et al., 2022). Between decentralised and centralised methods, lie CTDE approaches (Lowe et al., 2017; Papoudakis et al., 2021; Yu et al., 2022).

Due to the widespread availability of data, machine learning (ML) algorithms are increasingly being implemented in distributed topologies, wherein various nodes collaborate to train ML models via the coordination of a central server. However, distributed learning approaches face significant vulnerabilities, primarily stemming from two potential threats. Firstly, the presence of Byzantine nodes poses a risk of corrupting the learning process by transmitting inaccurate information to the server. Secondly, a curious server may compromise the privacy of individual nodes, sometimes reconstructing the entirety of the nodes' data. Homomorphic encryption (HE) has emerged as a leading security measure to preserve privacy in distributed learning under non-Byzantine scenarios. However, the extensive computational demands of HE, particularly for high-dimensional ML models, have deterred attempts to design purely homomorphic operators for non-linear robust aggregators. This paper introduces SABLE, the first homomorphic and Byzantine robust distributed learning algorithm. SABLE leverages HTS, a novel and efficient homomorphic operator implementing the prominent coordinate-wise trimmed mean robust aggregator. Designing HTS enables us to implement HMED, a novel homomorphic median aggregator. Extensive experiments on standard ML tasks demonstrate that SABLE achieves practical execution times while maintaining an ML accuracy comparable to its non-private counterpart.

You probably know Michelle Zauner best as the frontwoman of the band Japanese Breakfast, or perhaps as the author of her recent bestselling memoir Crying in H Mart. But the multihyphenate has yet another role to add to her résumé: video game composer. First announced in 2017, Sable is a sprawling adventure game about the titular young hero venturing across a desert planet to return to her family of nomads. Zauner provides the musical backbone to Sable's journey, crafting a set of themes big and small to deepen the game's world. Coming from the world of indie rock, though, posed an interesting set of challenges for the artist--but ones that a life of playing fantasy role-playing video games like this one prepared her for.

Last year was an unquestionably great year for gamers, with a wide variety of titles that pushed the medium forward and were just downright fun to play. Whether you're on a PlayStation 4, Xbox One, PC, Nintendo Switch or a smartphone, there's something to look forward to over the next few months. Here's a look at the video games we can't wait to play in 2019, from more serious fare like Anthem and Last of Us Part II to the supremely silly seeming Untitled Goose Game. Set on an alien world abandoned by its god-like creators, Anthem puts you in the shoes (or exosuit) of an armor-clad Freelancer, encouraging you to band together with your real-world friends as you explore the planet and keep the forces threatening humanity's continued existence at bay. When you're not protecting your species, you can spend time customizing your armor, unlocking new skills, and flying around like your second-favorite billionaire superhero.

E3 is widely considered a conference for big games, and understandably so; the largest publishers in the industry dominate the event, debuting trailers and news for the most expensive and expansive videogames they could possibly produce. But it's not impossible to find compelling independent games at the show, either: here are our picks for five that you'll want to keep your eyes on in the months to come. NeoCab is a game about the emotional labor of the gig economy, in a moody cyberpunk futurescape. You play one of the last human cab drivers, competing against an army of automated cars. The narrative forces you to balance the emotional health of your protagonist with the brutal needs of the job, as you struggle to barely--just barely--eke out a living.