Content Delivery Networks carry the majority of Internet traffic, and the increasing demand for video content as a major IP traffic across the Internet highlights the importance of caching and prefetching optimization algorithms. Prefetching aims to make data available in the cache before the requester places its request to reduce access time and improve the Quality of Experience on the user side. Prefetching is well investigated in operating systems, compiler instructions, in-memory cache, local storage systems, high-speed networks, and cloud systems. Traditional prefetching techniques are well adapted to a particular access pattern, but fail to adapt to sudden variations or randomization in workloads. This paper explores the use of reinforcement learning to tackle the changes in user access patterns and automatically adapt over time. To this end, we propose, DeePref, a Deep Reinforcement Learning agent for online video content prefetching in Content Delivery Networks. DeePref is a prefetcher implemented on edge networks and is agnostic to hardware design, operating systems, and applications. Our results show that DeePref DRQN, using a real-world dataset, achieves a 17% increase in prefetching accuracy and a 28% increase in prefetching coverage on average compared to baseline approaches that use video content popularity as a building block to statically or dynamically make prefetching decisions. We also study the possibility of transfer learning of statistical models from one edge network into another, where unseen user requests from unknown distribution are observed. In terms of transfer learning, the increase in prefetching accuracy and prefetching coverage are [$30%$, $10%$], respectively. Our source code will be available on Github.

Attention mechanisms have exhibited promising potential in enhancing learning models by identifying salient portions of input data. This is particularly valuable in scenarios where limited training samples are accessible due to challenges in data collection and labeling. Drawing inspiration from human recognition processes, we posit that an AI baseline's performance could be more accurate and dependable if it is exposed to essential segments of raw data rather than the entire input dataset, akin to human perception. However, the task of selecting these informative data segments, referred to as hard attention finding, presents a formidable challenge. In situations with few training samples, existing studies struggle to locate such informative regions due to the large number of training parameters that cannot be effectively learned from the available limited samples. In this study, we introduce a novel and practical framework for achieving explainable hard attention finding, specifically tailored for few-shot learning scenarios, called FewXAT. Our approach employs deep reinforcement learning to implement the concept of hard attention, directly impacting raw input data and thus rendering the process interpretable for human understanding. Through extensive experimentation across various benchmark datasets, we demonstrate the efficacy of our proposed method.

The rapid increase in the number of cyber-attacks in recent years raises the need for principled methods for defending networks against malicious actors. Deep reinforcement learning (DRL) has emerged as a promising approach for mitigating these attacks. However, while DRL has shown much potential for cyber-defence, numerous challenges must be overcome before DRL can be applied to autonomous cyber-operations (ACO) at scale. Principled methods are required for environments that confront learners with very high-dimensional state spaces, large multi-discrete action spaces, and adversarial learning. Recent works have reported success in solving these problems individually. There have also been impressive engineering efforts towards solving all three for real-time strategy games. However, applying DRL to the full ACO problem remains an open challenge. Here, we survey the relevant DRL literature and conceptualize an idealised ACO-DRL agent. We provide: i.) A summary of the domain properties that define the ACO problem; ii.) A comprehensive evaluation of the extent to which domains used for benchmarking DRL approaches are comparable to ACO; iii.) An overview of state-of-the-art approaches for scaling DRL to domains that confront learners with the curse of dimensionality, and; iv.) A survey and critique of current methods for limiting the exploitability of agents within adversarial settings from the perspective of ACO. We conclude with open research questions that we hope will motivate future directions for researchers and practitioners working on ACO.

Inspired by biological motion generation, central pattern generators (CPGs) is frequently employed in legged robot locomotion control to produce natural gait pattern with low-dimensional control signals. However, the limited adaptability and stability over complex terrains hinder its application. To address this issue, this paper proposes a terrain-adaptive locomotion control method that incorporates deep reinforcement learning (DRL) framework into CPG, where the CPG model is responsible for the generation of synchronized signals, providing basic locomotion gait, while DRL is integrated to enhance the adaptability of robot towards uneven terrains by adjusting the parameters of CPG mapping functions. The experiments conducted on the hexapod robot in Isaac Gym simulation environment demonstrated the superiority of the proposed method in terrain-adaptability, convergence rate and reward design complexity.

Fact-checking is a crucial task as it ensures the prevention of misinformation. However, manual fact-checking cannot keep up with the rate at which false information is generated and disseminated online. Automated fact-checking by machines is significantly quicker than by humans. But for better trust and transparency of these automated systems, explainability in the fact-checking process is necessary. Fact-checking often entails contrasting a factual assertion with a body of knowledge for such explanations. An effective way of representing knowledge is the Knowledge Graph (KG). There have been sufficient works proposed related to fact-checking with the usage of KG but not much focus is given to the application of reinforcement learning (RL) in such cases. To mitigate this gap, we propose an RL-based KG reasoning approach for explainable fact-checking. Extensive experiments on FB15K-277 and NELL-995 datasets reveal that reasoning over a KG is an effective way of producing human-readable explanations in the form of paths and classifications for fact claims. The RL reasoning agent computes a path that either proves or disproves a factual claim, but does not provide a verdict itself. A verdict is reached by a voting mechanism that utilizes paths produced by the agent. These paths can be presented to human readers so that they themselves can decide whether or not the provided evidence is convincing or not. This work will encourage works in this direction for incorporating RL for explainable fact-checking as it increases trustworthiness by providing a human-in-the-loop approach.

Posterior sampling allows the exploitation of prior knowledge of the environment's transition dynamics to improve the sample efficiency of reinforcement learning. The prior is typically specified as a class of parametric distributions, a task that can be cumbersome in practice, often resulting in the choice of uninformative priors. In this work, we propose a novel posterior sampling approach in which the prior is given as a (partial) causal graph over the environment's variables. The latter is often more natural to design, such as listing known causal dependencies between biometric features in a medical treatment study. Specifically, we propose a hierarchical Bayesian procedure, called C-PSRL, simultaneously learning the full causal graph at the higher level and the parameters of the resulting factored dynamics at the lower level. For this procedure, we provide an analysis of its Bayesian regret, which explicitly connects the regret rate with the degree of prior knowledge. Our numerical evaluation conducted in illustrative domains confirms that C-PSRL strongly improves the efficiency of posterior sampling with an uninformative prior while performing close to posterior sampling with the full causal graph.

In the domain of Federated Learning (FL) systems, recent cutting-edge methods heavily rely on ideal conditions convergence analysis. Specifically, these approaches assume that the training datasets on IoT devices possess similar attributes to the global data distribution. However, this approach fails to capture the full spectrum of data characteristics in real-time sensing FL systems. In order to overcome this limitation, we suggest a new approach system specifically designed for IoT networks with real-time sensing capabilities. Our approach takes into account the generalization gap due to the user's data sampling process. By effectively controlling this sampling process, we can mitigate the overfitting issue and improve overall accuracy. In particular, We first formulate an optimization problem that harnesses the sampling process to concurrently reduce overfitting while maximizing accuracy. In pursuit of this objective, our surrogate optimization problem is adept at handling energy efficiency while optimizing the accuracy with high generalization. To solve the optimization problem with high complexity, we introduce an online reinforcement learning algorithm, named Sample-driven Control for Federated Learning (SCFL) built on the Soft Actor-Critic (A2C) framework. This enables the agent to dynamically adapt and find the global optima even in changing environments. By leveraging the capabilities of SCFL, our system offers a promising solution for resource allocation in FL systems with real-time sensing capabilities.

Discovering all useful solutions for a given task is crucial for transferable RL agents, to account for changes in the task or transition dynamics. This is not considered by classical RL algorithms that are only concerned with finding the optimal policy, given the current task and dynamics. We propose a simple method for discovering all possible solutions of a given task, to obtain an agent that performs well in the transfer setting and adapts quickly to changes in the task or transition dynamics. Our method iteratively learns a set of policies, while each subsequent policy is constrained to yield a solution that is unlikely under all previous policies. Unlike prior methods, our approach does not require learning additional models for novelty detection and avoids balancing task and novelty reward signals, by directly incorporating the constraint into the action selection and optimization steps.

Plasticity, the ability of a neural network to evolve with new data, is crucial for high-performance and sample-efficient visual reinforcement learning (VRL). Although methods like resetting and regularization can potentially mitigate plasticity loss, the influences of various components within the VRL framework on the agent's plasticity are still poorly understood. In this work, we conduct a systematic empirical exploration focusing on three primary underexplored facets and derive the following insightful conclusions: (1) data augmentation is essential in maintaining plasticity; (2) the critic's plasticity loss serves as the principal bottleneck impeding efficient training; and (3) without timely intervention to recover critic's plasticity in the early stages, its loss becomes catastrophic. These insights suggest a novel strategy to address the high replay ratio (RR) dilemma, where exacerbated plasticity loss hinders the potential improvements of sample efficiency brought by increased reuse frequency. Rather than setting a static RR for the entire training process, we propose Adaptive RR, which dynamically adjusts the RR based on the critic's plasticity level. Extensive evaluations indicate that Adaptive RR not only avoids catastrophic plasticity loss in the early stages but also benefits from more frequent reuse in later phases, resulting in superior sample efficiency.

Nowadays, realistic simulation environments are essential to validate and build reliable robotic solutions. This is particularly true when using Reinforcement Learning (RL) based control policies. To this end, both robotics and RL developers need tools and workflows to create physically accurate simulations and synthetic datasets. Gazebo, MuJoCo, Webots, Pybullets or Isaac Sym are some of the many tools available to simulate robotic systems. Developing learning-based methods for space navigation is, due to the highly complex nature of the problem, an intensive data-driven process that requires highly parallelized simulations. When it comes to the control of spacecrafts, there is no easy to use simulation library designed for RL. We address this gap by harnessing the capabilities of NVIDIA Isaac Gym, where both physics simulation and the policy training reside on GPU. Building on this tool, we provide an open-source library enabling users to simulate thousands of parallel spacecrafts, that learn a set of maneuvering tasks, such as position, attitude, and velocity control. These tasks enable to validate complex space scenarios, such as trajectory optimization for landing, docking, rendezvous and more.