We study the problem of multi-agent reinforcement learning (multi-agent RL) with differential privacy (DP) constraints. This is well-motivated by various real-world applications involving sensitive data, where it is critical to protect users' private information. We first extend the definitions of Joint DP (JDP) and Local DP (LDP) to two-player zero-sum episodic Markov Games, where both definitions ensure trajectory-wise privacy protection. Then we design a provably efficient algorithm based on optimistic Nash value iteration and privatization of Bernstein-type bonuses. The algorithm is able to satisfy JDP and LDP requirements when instantiated with appropriate privacy mechanisms. Furthermore, for both notions of DP, our regret bound generalizes the best known result under the single-agent RL case, while our regret could also reduce to the best known result for multi-agent RL without privacy constraints. To the best of our knowledge, these are the first line of results towards understanding trajectory-wise privacy protection in multi-agent RL.

Footballing robots have had an upgrade. Two-legged robots trained using deep reinforcement learning, which is driven by artificial intelligence, can walk, turn to kick a ball and get up after falling faster than robots working from scripted lessons. Guy Lever at Google DeepMind and his colleagues put battery-powered Robotis OP3 robots, which are about 50 centimetres tall and have 20 joints, through 240 hours of deep reinforcement learning. This technique combines two key tenets of AI training: reinforcement learning sees agents gaining skills through trial and error, with a target of being rewarded for choosing correctly more often than choosing wrongly, while deep learning uses layers of neural networks – attempts to mimic the human brain – to analyse patterns within the data the AI is shown. The researchers compared their bots against robots working from pre-scripted skills.

Eye-tracking applications that utilize the human gaze in video understanding tasks have become increasingly important. To effectively automate the process of video analysis based on eye-tracking data, it is important to accurately replicate human gaze behavior. However, this task presents significant challenges due to the inherent complexity and ambiguity of human gaze patterns. In this work, we introduce a novel method for simulating human gaze behavior. Our approach uses a transformer-based reinforcement learning algorithm to train an agent that acts as a human observer, with the primary role of watching videos and simulating human gaze behavior. We employed an eye-tracking dataset gathered from videos generated by the VirtualHome simulator, with a primary focus on activity recognition. Our experimental results demonstrate the effectiveness of our gaze prediction method by highlighting its capability to replicate human gaze behavior and its applicability for downstream tasks where real human-gaze is used as input.

In the near future, mobile networks are expected to broaden their services and coverage to accommodate a larger user base and diverse user needs. Thus, they will increasingly rely on artificial intelligence (AI) to manage network operation and control costs, undertaking complex decision-making roles. This shift will necessitate the application of techniques that incorporate critical thinking abilities, including reasoning and planning. Symbolic AI techniques already facilitate critical thinking based on existing knowledge. Yet, their use in telecommunications is hindered by the high cost of mostly manual curation of this knowledge and high computational complexity of reasoning tasks. At the same time, there is a spurt of innovations in industries such as telecommunications due to Generative AI (GenAI) technologies, operating independently of human-curated knowledge. However, their capacity for critical thinking remains uncertain. This paper aims to address this gap by examining the current status of GenAI algorithms with critical thinking capabilities and investigating their potential applications in telecom networks. Specifically, the aim of this study is to offer an introduction to the potential utilization of GenAI for critical thinking techniques in mobile networks, while also establishing a foundation for future research.

This study introduces the Instance-Aware Index Advisor (IA2), a novel deep reinforcement learning (DRL)-based approach for optimizing index selection in databases facing large action spaces of potential candidates. IA2 introduces the Twin Delayed Deep Deterministic Policy Gradient - Temporal Difference State-Wise Action Refinery (TD3-TD-SWAR) model, enabling efficient index selection by understanding workload-index dependencies and employing adaptive action masking. This method includes a comprehensive workload model, enhancing its ability to adapt to unseen workloads and ensuring robust performance across diverse database environments. Evaluation on benchmarks such as TPC-H reveals IA2's suggested indexes' performance in enhancing runtime, securing a 40% reduction in runtime for complex TPC-H workloads compared to scenarios without indexes, and delivering a 20% improvement over existing state-of-the-art DRL-based index advisors.

We study the problem of online sequential decision-making given auxiliary demonstrations from experts who made their decisions based on unobserved contextual information. These demonstrations can be viewed as solving related but slightly different tasks than what the learner faces. This setting arises in many application domains, such as self-driving cars, healthcare, and finance, where expert demonstrations are made using contextual information, which is not recorded in the data available to the learning agent. We model the problem as a zero-shot meta-reinforcement learning setting with an unknown task distribution and a Bayesian regret minimization objective, where the unobserved tasks are encoded as parameters with an unknown prior. We propose the Experts-as-Priors algorithm (ExPerior), a non-parametric empirical Bayes approach that utilizes the principle of maximum entropy to establish an informative prior over the learner's decision-making problem. This prior enables the application of any Bayesian approach for online decision-making, such as posterior sampling. We demonstrate that our strategy surpasses existing behaviour cloning and online algorithms for multi-armed bandits and reinforcement learning, showcasing the utility of our approach in leveraging expert demonstrations across different decision-making setups.

Reinforcement learning (RL) is a promising approach to generate treatment policies for sepsis patients in intensive care. While retrospective evaluation metrics show decreased mortality when these policies are followed, studies with clinicians suggest their recommendations are often spurious. We propose that these shortcomings may be due to lack of diversity in observed actions and outcomes in the training data, and we construct experiments to investigate the feasibility of predicting sepsis disease severity changes due to clinician actions. Preliminary results suggest incorporating action information does not significantly improve model performance, indicating that clinician actions may not be sufficiently variable to yield measurable effects on disease progression. We discuss the implications of these findings for optimizing sepsis treatment.

In the era of 6G, featuring compelling visions of intelligent transportation system, digital twins, remote surveillance is poised to become a ubiquitous practice. The substantial data volume and frequent updates present challenges in wireless networks. To address this, we propose a novel agent-driven generative semantic communication (A-GSC) framework based on reinforcement learning. In contrast to the existing research on semantic communication (SemCom), which mainly focuses on semantic compression or semantic sampling, we seamlessly cascade both together by jointly considering the intrinsic attributes of source information and the contextual information regarding the task. Notably, the introduction of the generative artificial intelligence (GAI) enables the independent design of semantic encoders and decoders. In this work, we develop an agent-assisted semantic encoder leveraging the knowledge based soft actor-critic algorithm, which can track the semantic changes, channel condition, and sampling intervals, so as to perform adaptive semantic sampling. Accordingly, we design a semantic decoder with both predictive and generative capabilities, which consists of two tailored modules. Moreover, the effectiveness of the designed models has been verified based on the dataset generated from CDNet2014, and the performance gain of the overall A-GSC framework in both energy saving and reconstruction accuracy have been demonstrated.

While reinforcement learning (RL) algorithms have been successfully applied across numerous sequential decision-making problems, their generalization to unforeseen testing environments remains a significant concern. In this paper, we study the problem of out-of-distribution (OOD) detection in RL, which focuses on identifying situations at test time that RL agents have not encountered in their training environments. We first propose a clarification of terminology for OOD detection in RL, which aligns it with the literature from other machine learning domains. We then present new benchmark scenarios for OOD detection, which introduce anomalies with temporal autocorrelation into different components of the agent-environment loop. We argue that such scenarios have been understudied in the current literature, despite their relevance to real-world situations. Confirming our theoretical predictions, our experimental results suggest that state-of-the-art OOD detectors are not able to identify such anomalies. To address this problem, we propose a novel method for OOD detection, which we call DEXTER (Detection via Extraction of Time Series Representations). By treating environment observations as time series data, DEXTER extracts salient time series features, and then leverages an ensemble of isolation forest algorithms to detect anomalies. We find that DEXTER can reliably identify anomalies across benchmark scenarios, exhibiting superior performance compared to both state-of-the-art OOD detectors and high-dimensional changepoint detectors adopted from statistics.

Advances in Tiny Machine Learning (TinyML) have bolstered the creation of smart industry solutions, including smart agriculture, healthcare and smart cities. Whilst related research contributes to enabling TinyML solutions on constrained hardware, there is a need to amplify real-world applications by optimising energy consumption in battery-powered systems. The work presented extends and contributes to TinyML research by optimising battery-powered image-based anomaly detection Internet of Things (IoT) systems. Whilst previous work in this area has yielded the capabilities of on-device inferencing and training, there has yet to be an investigation into optimising the management of such capabilities using machine learning approaches, such as Reinforcement Learning (RL), to improve the deployment battery life of such systems. Using modelled simulations, the battery life effects of an RL algorithm are benchmarked against static and dynamic optimisation approaches, with the foundation laid for a hardware benchmark to follow. It is shown that using RL within a TinyML-enabled IoT system to optimise the system operations, including cloud anomaly processing and on-device training, yields an improved battery life of 22.86% and 10.86% compared to static and dynamic optimisation approaches respectively. The proposed solution can be deployed to resource-constrained hardware, given its low memory footprint of 800 B, which could be further reduced. This further facilitates the real-world deployment of such systems, including key sectors such as smart agriculture.