The current scenario of IoT is witnessing a constant increase on the volume of data, which is generated in constant stream, calling for novel architectural and logical solutions for processing it. Moving the data handling towards the edge of the computing spectrum guarantees better distribution of load and, in principle, lower latency and better privacy. However, managing such a structure is complex, especially when requirements, also referred to Service Level Objectives (SLOs), specified by applications' owners and infrastructure managers need to be ensured. Despite the rich number of proposals of Machine Learning (ML) based management solutions, researchers and practitioners yet struggle to guarantee long-term prediction and control, and accurate troubleshooting. Therefore, we present a novel ML paradigm based on Active Inference (AIF) -- a concept from neuroscience that describes how the brain constantly predicts and evaluates sensory information to decrease long-term surprise. We implement it and evaluate it in a heterogeneous real stream processing use case, where an AIF-based agent continuously optimizes the fulfillment of three SLOs for three autonomous driving services running on multiple devices. The agent used causal knowledge to gradually develop an understanding of how its actions are related to requirements fulfillment, and which configurations to favor. Through this approach, our agent requires up to thirty iterations to converge to the optimal solution, showing the capability of offering accurate results in a short amount of time. Furthermore, thanks to AIF and its causal structures, our method guarantees full transparency on the decision making, making the interpretation of the results and the troubleshooting effortless.

End-to-end autonomous driving offers a streamlined alternative to the traditional modular pipeline, integrating perception, prediction, and planning within a single framework. While Deep Reinforcement Learning (DRL) has recently gained traction in this domain, existing approaches often overlook the critical connection between feature extraction of DRL and perception. In this paper, we bridge this gap by mapping the DRL feature extraction network directly to the perception phase, enabling clearer interpretation through semantic segmentation. By leveraging Bird's-Eye-View (BEV) representations, we propose a novel DRL-based end-to-end driving framework that utilizes multi-sensor inputs to construct a unified three-dimensional understanding of the environment. This BEV-based system extracts and translates critical environmental features into high-level abstract states for DRL, facilitating more informed control. Extensive experimental evaluations demonstrate that our approach not only enhances interpretability but also significantly outperforms state-of-the-art methods in autonomous driving control tasks, reducing the collision rate by 20%.

While Reinforcement Learning (RL) aims to train an agent from a reward function in a given environment, Inverse Reinforcement Learning (IRL) seeks to recover the reward function from observing an expert's behavior. It is well known that, in general, various reward functions can lead to the same optimal policy, and hence, IRL is ill-defined. However, [1] showed that, if we observe two or more experts with different discount factors or acting in different environments, the reward function can under certain conditions be identified up to a constant. This work starts by showing an equivalent identifiability statement from multiple experts in tabular MDPs based on a rank condition, which is easily verifiable and is shown to be also necessary. We then extend our result to various different scenarios, i.e., we characterize reward identifiability in the case where the reward function can be represented as a linear combination of given features, making it more interpretable, or when we have access to approximate transition matrices. Even when the reward is not identifiable, we provide conditions characterizing when data on multiple experts in a given environment allows to generalize and train an optimal agent in a new environment. Our theoretical results on reward identifiability and generalizability are validated in various numerical experiments.

We present a random measure approach for modeling exploration, i.e., the execution of measure-valued controls, in continuous-time reinforcement learning (RL) with controlled diffusion and jumps. First, we consider the case when sampling the randomized control in continuous time takes place on a discrete-time grid and reformulate the resulting stochastic differential equation (SDE) as an equation driven by suitable random measures. The construction of these random measures makes use of the Brownian motion and the Poisson random measure (which are the sources of noise in the original model dynamics) as well as the additional random variables, which are sampled on the grid for the control execution. Then, we prove a limit theorem for these random measures as the mesh-size of the sampling grid goes to zero, which leads to the grid-sampling limit SDE that is jointly driven by white noise random measures and a Poisson random measure. We also argue that the grid-sampling limit SDE can substitute the exploratory SDE and the sample SDE of the recent continuous-time RL literature, i.e., it can be applied for the theoretical analysis of exploratory control problems and for the derivation of learning algorithms.

As financial markets grow increasingly complex in the big data era, accurate stock prediction has become more critical. Traditional time series models, such as GRUs, have been widely used but often struggle to capture the intricate nonlinear dynamics of markets, particularly in the flexible selection and effective utilization of key historical information. Recently, methods like Graph Neural Networks and Reinforcement Learning have shown promise in stock prediction but require high data quality and quantity, and they tend to exhibit instability when dealing with data sparsity and noise. Moreover, the training and inference processes for these models are typically complex and computationally expensive, limiting their broad deployment in practical applications. Existing approaches also generally struggle to capture unobservable latent market states effectively, such as market sentiment and expectations, microstructural factors, and participant behavior patterns, leading to an inadequate understanding of market dynamics and subsequently impact prediction accuracy. To address these challenges, this paper proposes a stock prediction model, MCI-GRU, based on a multi-head cross-attention mechanism and an improved GRU. First, we enhance the GRU model by replacing the reset gate with an attention mechanism, thereby increasing the model's flexibility in selecting and utilizing historical information. Second, we design a multi-head cross-attention mechanism for learning unobservable latent market state representations, which are further enriched through interactions with both temporal features and cross-sectional features. Finally, extensive experiments on four main stock markets show that the proposed method outperforms SOTA techniques across multiple metrics. Additionally, its successful application in real-world fund management operations confirms its effectiveness and practicality.

Humanoid robots offer significant versatility for performing a wide range of tasks, yet their basic ability to walk and run, especially at high velocities, remains a challenge. This letter presents a novel method that combines deep reinforcement learning with kinodynamic priors to achieve stable locomotion control (KSLC). KSLC promotes coordinated arm movements to counteract destabilizing forces, enhancing overall stability. Compared to the baseline method, KSLC provides more accurate tracking of commanded velocities and better generalization in velocity control. In simulation tests, the KSLC-enabled humanoid robot successfully tracked a target velocity of 3.5 m/s with reduced fluctuations. Sim-to-sim validation in a high-fidelity environment further confirmed its robust performance, highlighting its potential for real-world applications.

Cyber-attacks are becoming increasingly sophisticated and frequent, highlighting the importance of network intrusion detection systems. This paper explores the potential and challenges of using deep reinforcement learning (DRL) in network intrusion detection. It begins by introducing key DRL concepts and frameworks, such as deep Q-networks and actor-critic algorithms, and reviews recent research utilizing DRL for intrusion detection. The study evaluates challenges related to model training efficiency, detection of minority and unknown class attacks, feature selection, and handling unbalanced datasets. The performance of DRL models is comprehensively analyzed, showing that while DRL holds promise, many recent technologies remain underexplored. Some DRL models achieve state-of-the-art results on public datasets, occasionally outperforming traditional deep learning methods. The paper concludes with recommendations for enhancing DRL deployment and testing in real-world network scenarios, with a focus on Internet of Things intrusion detection. It discusses recent DRL architectures and suggests future policy functions for DRL-based intrusion detection. Finally, the paper proposes integrating DRL with generative methods to further improve performance, addressing current gaps and supporting more robust and adaptive network intrusion detection systems.

The goal of this work is to serve as a foundation for deep studies of the topology of state, action, and policy spaces in reinforcement learning. By studying these spaces from a mathematical perspective, we expect to gain more insight into how to build better algorithms to solve decision problems. Therefore, we focus on presenting the connection between the Banach fixed point theorem and the convergence of reinforcement learning algorithms, and we illustrate how the insights gained from this can practically help in designing more efficient algorithms. Before doing so, however, we first introduce relevant concepts such as metric spaces, normed spaces and Banach spaces for better understanding, before expressing the entire reinforcement learning problem in terms of Markov decision processes. This allows us to properly introduce the Banach contraction principle in a language suitable for reinforcement learning, and to write the Bellman equations in terms of operators on Banach spaces to show why reinforcement learning algorithms converge. Finally, we show how the insights gained from the mathematical study of convergence are helpful in reasoning about the best ways to make reinforcement learning algorithms more efficient.

Deep reinforcement learning has seen successful implementations on humanoid robots to achieve dynamic walking. However, these implementations have been so far successful in simple environments void of obstacles. In this paper, we aim to achieve bipedal locomotion in an environment where obstacles are present using a policy-based reinforcement learning. By adding simple distance reward terms to a state of art reward function that can achieve basic bipedal locomotion, the trained policy succeeds in navigating the robot towards the desired destination without colliding with the obstacles along the way.

Recent advances in automated essay scoring (AES) have shifted towards evaluating multiple traits to provide enriched feedback. Like typical AES systems, multi-trait AES employs the quadratic weighted kappa (QWK) to measure agreement with human raters, aligning closely with the rating schema; however, its non-differentiable nature prevents its direct use in neural network training. In this paper, we propose Scoring-aware Multi-reward Reinforcement Learning (SaMRL), which integrates actual evaluation schemes into the training process by designing QWK-based rewards with a mean-squared error penalty for multi-trait AES. Existing reinforcement learning (RL) applications in AES are limited to classification models despite associated performance degradation, as RL requires probability distributions; instead, we adopt an autoregressive score generation framework to leverage token generation probabilities for robust multi-trait score predictions. Empirical analyses demonstrate that SaMRL facilitates model training, notably enhancing scoring of previously inferior prompts.