相关论文: Multi-platform Version of StarCraft: Brood War in …

Containerisation is a popular deployment process for application-level virtualisation using a layer-based approach. Docker is a leading provider of containerisation, and through the Docker Hub, users can supply Docker images for sharing and…

Using a robotic platform for telepresence applications has gained paramount importance in this decade. Scenarios such as remote meetings, group discussions, and presentations/talks in seminars and conferences get much attention in this…

This article describes high-speed multiprocessor architecture for the concurrent analyzing information represented in analytic, graph- and table forms of associative relations to search, recognize and make a decision in n-dimensional vector…

We introduce Platform for Situated Intelligence, an open-source framework created to support the rapid development and study of multimodal, integrative-AI systems. The framework provides infrastructure for sensing, fusing, and making…

Since emerging edge applications such as Internet of Things (IoT) analytics and augmented reality have tight latency constraints, hardware AI accelerators have been recently proposed to speed up deep neural network (DNN) inference run by…

The burgeoning fields of robot learning and embodied AI have triggered an increasing demand for large quantities of data. However, collecting sufficient unbiased data from the target domain remains a challenge due to costly data collection…

Users of AI systems may rely upon them to produce plans for achieving desired objectives. Such AI systems should be able to compute obfuscated plans whose execution in adversarial situations protects privacy, as well as legible plans which…

In recent years, data-intensive applications have been increasingly deployed on cloud systems. Such applications utilize significant compute, memory, and I/O resources to process large volumes of data. Optimizing the performance and…

Inspired by the recent success of transformers in natural language processing and computer vision applications, we introduce a transformer-based neural architecture for two key StarCraft II (SC2) macromanagement tasks: global state and…

With the ever growing number of space debris in orbit, the need to prevent further space population is becoming more and more apparent. Refueling, servicing, inspection and deorbiting of spacecraft are some example missions that require…

We consider scenarios from the real-time strategy game StarCraft as new benchmarks for reinforcement learning algorithms. We propose micromanagement tasks, which present the problem of the short-term, low-level control of army members…

The reproducibility of software environments is a critical concern in modern software engineering, with ramifications ranging from the effectiveness of collaboration workflows to software supply chain security and scientific…

As artificial intelligence research advances, the platforms used to evaluate AI agents need to adapt and grow to continue to challenge them. We present the Polycraft World AI Lab (PAL), a task simulator with an API based on the Minecraft…

In recent years, there have been immense breakthroughs in Game AI research, particularly with Reinforcement Learning (RL). Despite their success, the underlying games are usually implemented with their own preset environments and game…

Decentralization, immutability and transparency make of Blockchain one of the most innovative technology of recent years. This paper presents an overview of solutions based on Blockchain technology for multi-agent robotic systems, and…

Reliable Docker-based environment construction is a dominant bottleneck for scaling execution-grounded training and evaluation of software engineering agents. We introduce DockSmith, a specialized agentic Docker builder designed to address…

IBM Research Castor, a cloud-native system for managing and deploying large numbers of AI time-series models in IoT applications, is described. Modelling code templates, in Python and R, following a typical machine-learning workflow are…

In the domain of combat simulations in support of wargaming, the development of intelligent agents has predominantly been characterized by rule-based, scripted methodologies with deep reinforcement learning (RL) approaches only recently…

Cross-platform robot control remains difficult because hardware interfaces, data formats, and control paradigms vary widely, which fragments toolchains and slows deployment. To address this, we present Control Your Robot, a modular,…

The use of container technology has skyrocketed during the last few years, with Docker as the leading container platform. Docker's online repository for publicly available container images, called Docker Hub, hosts over 3.5 million images…