Multi-agent reinforcement learning (MARL) research is inherently computationally expensive and it is often difficult to obtain a sufficient number of experiment samples to test hypotheses and make robust statistical claims. Furthermore, MARL algorithms are typically complex in their design and can be tricky to implement correctly. These aspects of MARL present a difficult challenge when it comes to creating useful software for advanced research. Our criteria for such software is that it should be simple enough to use to implement new ideas quickly, while at the same time be scalable and fast enough to test those ideas in a reasonable amount of time. In this preliminary technical report, we introduce Mava, a research library for MARL written purely in JAX, that aims to fulfill these criteria. We discuss the design and core features of Mava, and demonstrate its use and performance across a variety of environments. In particular, we show Mava's substantial speed advantage, with improvements of 10-100x compared to other popular MARL frameworks, while maintaining strong performance. This allows for researchers to test ideas in a few minutes instead of several hours. Finally, Mava forms part of an ecosystem of libraries that seamlessly integrate with each other to help facilitate advanced research in MARL. We hope Mava will benefit the community and help drive scientifically sound and statistically robust research in the field. The open-source repository for Mava is available at https://github.com/instadeepai/Mava.

The Video Game History Foundation set up shop back in 2017 and offers a gigantic collection of gaming-related archival materials, from magazines to art books and even source code. Previously, you'd have to make the trek to Oakland, California to peruse the archive, but that changes soon. The VGHF just announced a digital library that will offer remote access. These tools will be made available to researchers, academics and garden-variety gaming enthusiasts like the rest of us. The library will offer access to the collection "for free from anywhere in the world."

Data privacy concerns has made centralized training of data, which is scattered across silos, infeasible, leading to the need for collaborative learning frameworks. To address that, two prominent frameworks emerged, i.e., federated learning (FL) and split learning (SL). While FL has established various benchmark frameworks and research libraries,SL currently lacks a unified library despite its diversity in terms of label sharing, model aggregation, and cut layer choice. This lack of standardization makes comparing SL paradigms difficult. To address this, we propose SLPerf, a unified research framework and open research library for SL, and conduct extensive experiments on four widely-used datasets under both IID and Non-IID data settings. Our contributions include a comprehensive survey of recently proposed SL paradigms, a detailed benchmark comparison of different SL paradigms in different situations, and rich engineering take-away messages and research insights for improving SL paradigms. SLPerf can facilitate SL algorithm development and fair performance comparisons. The code is available at https://github.com/Rainysponge/Split-learning-Attacks .

In 2014 I optimistically wrote for the Knight Foundation blog that libraries could reinvent themselves in the digital era, tracing my own collaborations with the Internet Archive over the prior year and drawing from my opening keynote address to the 2012 IIPC General Assembly at the Library of Congress. Yet, reflecting back three years later, looking at just how adrift and leaderless so many research libraries have become in the digital era, unsure of how to reinvent themselves and often too arrogant and insular to reach out beyond the communities they have worked with for centuries, I am no longer so certain that research libraries and the academic communities that work most closely with them can genuinely reimagine themselves on their own. Community libraries have found great success reinventing themselves to better fit into modern lifestyles, from collaborative spaces to free wifi to ebooks to and even 3D printers and virtual reality systems, but research libraries as a whole seem to be struggling to find their footing in the digital era. What might they learn from the world of the commercial cloud and indeed the broader technological future of Silicon Valley? The commercial cloud has truly transformed how we think about computing in the modern era, from the shift from hardware to services and experts, the rise of seamless security and unimaginable deep learning systems accessible by a single API call.

Pylearn2 is a machine learning research library. This does not just mean that it is a collection of machine learning algorithms that share a common API; it means that it has been designed for flexibility and extensibility in order to facilitate research projects that involve new or unusual use cases. In this paper we give a brief history of the library, an overview of its basic philosophy, a summary of the library's architecture, and a description of how the Pylearn2 community functions socially.