Inside the Colosseum's Passage of Commodus, where emperors once walked One theory suggests the infamous Roman emperor survived an assassination attempt in the tunnel now open to the public. From October 2024 to September 2025, a team of experts restored part of the tunnel that's open to visitors for the first time. Breakthroughs, discoveries, and DIY tips sent six days a week. They say all roads lead to Rome . But in the Eternal City, all of the major roads were thought to lead somewhere very specific--a single column called the Milliarium Auereum, or the golden milestone.

Meticulously analysing the empirical strengths and weaknesses of reinforcement learning methods in hard (challenging) environments is essential to inspire innovations and assess progress in the field. In tabular reinforcement learning, there is no well-established standard selection of environments to conduct such analysis, which is partially due to the lack of a widespread understanding of the rich theory of hardness of environments. The goal of this paper is to unlock the practical usefulness of this theory through four main contributions. First, we present a systematic survey of the theory of hardness, which also identifies promising research directions. Second, we introduce $\texttt{Colosseum}$, a pioneering package that enables empirical hardness analysis and implements a principled benchmark composed of environments that are diverse with respect to different measures of hardness. Third, we present an empirical analysis that provides new insights into computable measures. Finally, we benchmark five tabular agents in our newly proposed benchmark. While advancing the theoretical understanding of hardness in non-tabular reinforcement learning remains essential, our contributions in the tabular setting are intended as solid steps towards a principled non-tabular benchmark. Accordingly, we benchmark four agents in non-tabular versions of $\texttt{Colosseum}$ environments, obtaining results that demonstrate the generality of tabular hardness measures.

Finally, we benchmark five tabular agents in our newly proposed benchmark.

The performances of the agents are in line with the results reported in Osband et al.

Finally, we benchmark five tabular agents in our newly proposed benchmark.

Meticulously analysing the empirical strengths and weaknesses of reinforcement learning methods in hard (challenging) environments is essential to inspire innovations and assess progress in the field. In tabular reinforcement learning, there is no well-established standard selection of environments to conduct such analysis, which is partially due to the lack of a widespread understanding of the rich theory of hardness of environments. The goal of this paper is to unlock the practical usefulness of this theory through four main contributions. First, we present a systematic survey of the theory of hardness, which also identifies promising research directions. Second, we introduce \texttt{Colosseum}, a pioneering package that enables empirical hardness analysis and implements a principled benchmark composed of environments that are diverse with respect to different measures of hardness.

Open Radio Access Network (RAN) architectures will enable interoperability, openness and programmable data-driven control in next generation cellular networks. However, developing and testing efficient solutions that generalize across heterogeneous cellular deployments and scales, and that optimize network performance in such diverse environments is a complex task that is still largely unexplored. In this paper we present OpenRAN Gym, a unified, open, and O-RAN-compliant experimental toolbox for data collection, design, prototyping and testing of end-to-end data-driven control solutions for next generation Open RAN systems. OpenRAN Gym extends and combines into a unique solution several software frameworks for data collection of RAN statistics and RAN control, and a lightweight O-RAN near-real-time RAN Intelligent Controller (RIC) tailored to run on experimental wireless platforms. We first provide an overview of the various architectural components of OpenRAN Gym and describe how it is used to collect data and design, train and test artificial intelligence and machine learning O-RAN-compliant applications (xApps) at scale. We then describe in detail how to test the developed xApps on softwarized RANs and provide an example of two xApps developed with OpenRAN Gym that are used to control a network with 7 base stations and 42 users deployed on the Colosseum testbed. Finally, we show how solutions developed with OpenRAN Gym on Colosseum can be exported to real-world, heterogeneous wireless platforms, such as the Arena testbed and the POWDER and COSMOS platforms of the PAWR program. OpenRAN Gym and its software components are open-source and publicly-available to the research community. By guiding the readers through running experiments with OpenRAN Gym, we aim at providing a key reference for researchers and practitioners working on experimental Open RAN systems.

Colosseum is an open-access and publicly-available large-scale wireless testbed for experimental research via virtualized and softwarized waveforms and protocol stacks on a fully programmable, "white-box" platform. Through 256 state-of-the-art Software-defined Radios and a Massive Channel Emulator core, Colosseum can model virtually any scenario, enabling the design, development and testing of solutions at scale in a variety of deployments and channel conditions. These Colosseum radio-frequency scenarios are reproduced through high-fidelity FPGA-based emulation with finite-impulse response filters. Filters model the taps of desired wireless channels and apply them to the signals generated by the radio nodes, faithfully mimicking the conditions of real-world wireless environments. In this paper we describe the architecture of Colosseum and its experimentation and emulation capabilities. We then demonstrate the effectiveness of Colosseum for experimental research at scale through exemplary use cases including prevailing wireless technologies (e.g., cellular and Wi-Fi) in spectrum sharing and unmanned aerial vehicle scenarios. A roadmap for Colosseum future updates concludes the paper.

The latest AI project from the MIT Media Lab is demonstrating just how terrifying the prospects of deep learning can go. Welcome to the Nightmare Machine: an algorithm that has been trained to generate horrifying images. It is attempting to find the scariest faces and locations possible, and gets humans to tell it which are the worst. The first aspect of the project, Haunted Faces, is truly terrifying. The team behind the project, led by Iyad Rahwan, associate professor at MIT Media Lab, used deep learning to generate new faces, before dropping "a hint of scariness" onto the generated faces in the spirit of Halloween.

Launched in 2016, SC2's goal is to create a collaborative machine-learning competition to address radio frequency (RF) spectrum challenges. DARPA experts created SC2 to help users of the existing radio spectrum overcome the problem of clogged spectrum. Demand for radio spectrum has grown steadily over the past century, and in the past several years has increased at a rate of 50 per-cent per year. SC2 wants to move away from traditional ways of communicating via one frequency. As Paul Tilghman explained during his keynote speech at NIWeek, one of the biggest obstacles in spectrum management is that "frequency isolation completely dominates our spectrum landscape."