In this paper, we study representation learning in partially observable Markov Decision Processes (POMDPs), where the agent learns a decoder function that maps a series of high-dimensional raw observations to a compact representation and uses it for more efficient exploration and planning. We focus our attention on the sub-classes of \textit{$\gamma$-observable} and \textit{decodable POMDPs}, for which it has been shown that statistically tractable learning is possible, but there has not been any computationally efficient algorithm. We first present an algorithm for decodable POMDPs that combines maximum likelihood estimation (MLE) and optimism in the face of uncertainty (OFU) to perform representation learning and achieve efficient sample complexity, while only calling supervised learning computational oracles. We then show how to adapt this algorithm to also work in the broader class of $\gamma$-observable POMDPs.

This paper introduces the Adaptive Learning Path Navigation (ALPN) system, a novel approach for enhancing E-learning platforms by providing highly adaptive learning paths for students. The ALPN system integrates the Attentive Knowledge Tracing (AKT) model, which assesses students' knowledge states, with the proposed Entropy-enhanced Proximal Policy Optimization (EPPO) algorithm. This new algorithm optimizes the recommendation of learning materials. By harmonizing these models, the ALPN system tailors the learning path to students' needs, significantly increasing learning effectiveness. Experimental results demonstrate that the ALPN system outperforms previous research by 8.2% in maximizing learning outcomes and provides a 10.5% higher diversity in generating learning paths. The proposed system marks a significant advancement in adaptive E-learning, potentially transforming the educational landscape in the digital era.

In cooperative Multi-Agent Reinforcement Learning (MARL) agents are required to learn behaviours as a team to achieve a common goal. However, while learning a task, some agents may end up learning sub-optimal policies, not contributing to the objective of the team. Such agents are called lazy agents due to their non-cooperative behaviours that may arise from failing to understand whether they caused the rewards. As a consequence, we observe that the emergence of cooperative behaviours is not necessarily a byproduct of being able to solve a task as a team. In this paper, we investigate the applications of causality in MARL and how it can be applied in MARL to penalise these lazy agents. We observe that causality estimations can be used to improve the credit assignment to the agents and show how it can be leveraged to improve independent learning in MARL. Furthermore, we investigate how Amortized Causal Discovery can be used to automate causality detection within MARL environments. The results demonstrate that causality relations between individual observations and the team reward can be used to detect and punish lazy agents, making them develop more intelligent behaviours. This results in improvements not only in the overall performances of the team but also in their individual capabilities. In addition, results show that Amortized Causal Discovery can be used efficiently to find causal relations in MARL.

In this paper, we present a kernel-based, multi-task Gaussian Process (GP) model for approximating the underlying function of an individual's mobility state using a time-inhomogeneous Markov Process with two states: moves and pauses. Our approach accounts for the correlations between the transition probabilities by creating a covariance matrix over the tasks. We also introduce time-variability by assuming that an individual's transition probabilities vary over time in response to exogenous variables. We enforce the stochasticity and non-negativity constraints of probabilities in a Markov process through the incorporation of a set of constraint points in the GP. We also discuss opportunities to speed up GP estimation and inference in this context by exploiting Toeplitz and Kronecker product structures. Our numerical experiments demonstrate the ability of our formulation to enforce the desired constraints while learning the functional form of transition probabilities.

We study the problem of computing an optimal policy of an infinite-horizon discounted constrained Markov decision process (constrained MDP). Despite the popularity of Lagrangian-based policy search methods used in practice, the oscillation of policy iterates in these methods has not been fully understood, bringing out issues such as violation of constraints and sensitivity to hyper-parameters. To fill this gap, we employ the Lagrangian method to cast a constrained MDP into a constrained saddle-point problem in which max/min players correspond to primal/dual variables, respectively, and develop two single-time-scale policy-based primal-dual algorithms with non-asymptotic convergence of their policy iterates to an optimal constrained policy. Specifically, we first propose a regularized policy gradient primal-dual (RPG-PD) method that updates the policy using an entropy-regularized policy gradient, and the dual via a quadratic-regularized gradient ascent, simultaneously. We prove that the policy primal-dual iterates of RPG-PD converge to a regularized saddle point with a sublinear rate, while the policy iterates converge sublinearly to an optimal constrained policy. We further instantiate RPG-PD in large state or action spaces by including function approximation in policy parametrization, and establish similar sublinear last-iterate policy convergence. Second, we propose an optimistic policy gradient primal-dual (OPG-PD) method that employs the optimistic gradient method to update primal/dual variables, simultaneously. We prove that the policy primal-dual iterates of OPG-PD converge to a saddle point that contains an optimal constrained policy, with a linear rate. To the best of our knowledge, this work appears to be the first non-asymptotic policy last-iterate convergence result for single-time-scale algorithms in constrained MDPs.

In this work, we describe a novel method of training an embedding-matching word-level connectionist temporal classification (CTC) automatic speech recognizer (ASR) such that it directly produces word start times and durations, required by many real-world applications, in addition to the transcription. The word timestamps enable the ASR to output word segmentations and word confusion networks without relying on a secondary model or forced alignment process when testing. Our proposed system has similar word segmentation accuracy as a hybrid DNN-HMM (Deep Neural Network-Hidden Markov Model) system, with less than 3ms difference in mean absolute error in word start times on TIMIT data. At the same time, we observed less than 5% relative increase in the word error rate compared to the non-timestamped system when using the same audio training data and nearly identical model size. We also contribute more rigorous analysis of multiple-hypothesis embedding-matching ASR in general.

Cooperative multi-agent reinforcement learning (MARL) for navigation enables agents to cooperate to achieve their navigation goals. Using emergent communication, agents learn a communication protocol to coordinate and share information that is needed to achieve their navigation tasks. In emergent communication, symbols with no pre-specified usage rules are exchanged, in which the meaning and syntax emerge through training. Learning a navigation policy along with a communication protocol in a MARL environment is highly complex due to the huge state space to be explored. To cope with this complexity, this work proposes a novel neural network architecture, for jointly learning an adaptive state space abstraction and a communication protocol among agents participating in navigation tasks. The goal is to come up with an adaptive abstractor that significantly reduces the size of the state space to be explored, without degradation in the policy performance. Simulation results show that the proposed method reaches a better policy, in terms of achievable rewards, resulting in fewer training iterations compared to the case where raw states or fixed state abstraction are used. Moreover, it is shown that a communication protocol emerges during training which enables the agents to learn better policies within fewer training iterations.

The thesis advances the field of software security by providing knowledge and automation support for software vulnerability assessment using data-driven approaches. Software vulnerability assessment provides important and multifaceted information to prevent and mitigate dangerous cyber-attacks in the wild. The key contributions include a systematisation of knowledge, along with a suite of novel data-driven techniques and practical recommendations for researchers and practitioners in the area. The thesis results help improve the understanding and inform the practice of assessing ever-increasing vulnerabilities in real-world software systems. This in turn enables more thorough and timely fixing prioritisation and planning of these critical security issues.

Autonomous agents deployed in the real world need to be robust against adversarial attacks on sensory inputs. Robustifying agent policies requires anticipating the strongest attacks possible. We demonstrate that existing observation-space attacks on reinforcement learning agents have a common weakness: while effective, their lack of temporal consistency makes them detectable using automated means or human inspection. Detectability is undesirable to adversaries as it may trigger security escalations. We introduce perfect illusory attacks, a novel form of adversarial attack on sequential decision-makers that is both effective and provably statistically undetectable. We then propose the more versatile R-attacks, which result in observation transitions that are consistent with the state-transition function of the adversary-free environment and can be learned end-to-end. Compared to existing attacks, we empirically find R-attacks to be significantly harder to detect with automated methods, and a small study with human subjects suggests they are similarly harder to detect for humans. We propose that undetectability should be a central concern in the study of adversarial attacks on mixed-autonomy settings.

Optimal control of general nonlinear systems is a central challenge in automation. Enabled by powerful function approximators, data-driven approaches to control have recently successfully tackled challenging applications. However, such methods often obscure the structure of dynamics and control behind black-box over-parameterized representations, thus limiting our ability to understand closed-loop behavior. This paper adopts a hybrid-system view of nonlinear modeling and control that lends an explicit hierarchical structure to the problem and breaks down complex dynamics into simpler localized units. We consider a sequence modeling paradigm that captures the temporal structure of the data and derive an expectation-maximization (EM) algorithm that automatically decomposes nonlinear dynamics into stochastic piecewise affine models with nonlinear transition boundaries. Furthermore, we show that these time-series models naturally admit a closed-loop extension that we use to extract local polynomial feedback controllers from nonlinear experts via behavioral cloning. Finally, we introduce a novel hybrid relative entropy policy search (Hb-REPS) technique that incorporates the hierarchical nature of hybrid models and optimizes a set of time-invariant piecewise feedback controllers derived from a piecewise polynomial approximation of a global state-value function.