In real-world reinforcement learning (RL) scenarios, agents often encounter partial observability, where incomplete or noisy information obscures the true state of the environment. Partially Observable Markov Decision Processes (POMDPs) are commonly used to model these environments, but effective performance requires memory mechanisms to utilise past observations. While recurrence networks have traditionally addressed this need, transformer-based models have recently shown improved sample efficiency in RL tasks. However, their application to POMDPs remains underdeveloped, and their real-world deployment is constrained due to the high parameter count. This work introduces a novel bi-recurrent model architecture that improves sample efficiency and reduces model parameter count in POMDP scenarios. The architecture replaces the multiple feed forward layers with a single layer of bi-directional recurrence unit to better capture and utilize sequential dependencies and contextual information. This approach improves the model's ability to handle partial observability and increases sample efficiency, enabling effective learning from comparatively fewer interactions. To evaluate the performance of the proposed model architecture, experiments were conducted on a total of 23 POMDP environments. The proposed model architecture outperforms existing transformer-based, attention-based, and recurrence-based methods by a margin ranging from 87.39% to 482.04% on average across the 23 POMDP environments.

Photoplethysmography (PPG) signals encode information about relative changes in blood volume that can be used to assess various aspects of cardiac health non-invasively, e.g.\ to detect atrial fibrillation (AF) or predict blood pressure (BP). Deep networks are well-equipped to handle the large quantities of data acquired from wearable measurement devices. However, they lack interpretability and are prone to overfitting, leaving considerable risk for poor performance on unseen data and misdiagnosis. Here, we describe the use of two scalable uncertainty quantification techniques: Monte Carlo Dropout and the recently proposed Improved Variational Online Newton. These techniques are used to assess the trustworthiness of models trained to perform AF classification and BP regression from raw PPG time series. We find that the choice of hyperparameters has a considerable effect on the predictive performance of the models and on the quality and composition of predicted uncertainties. E.g. the stochasticity of the model parameter sampling determines the proportion of the total uncertainty that is aleatoric, and has varying effects on predictive performance and calibration quality dependent on the chosen uncertainty quantification technique and the chosen expression of uncertainty. We find significant discrepancy in the quality of uncertainties over the predicted classes, emphasising the need for a thorough evaluation protocol that assesses local and adaptive calibration. This work suggests that the choice of hyperparameters must be carefully tuned to balance predictive performance and calibration quality, and that the optimal parameterisation may vary depending on the chosen expression of uncertainty.

Classifiers are often deployed in contexts in which the independent and identically distributed (IID) assumption is violated, i.e., in which the data used to train the model and the future data to be classified are not drawn from the same distribution. This situation is generally referred to as dataset shift in the machine learning literature [Storkey, 2009]. In this context, three problems have gained increased attention in the last years. Classifier calibration [Flach and Webb, 2016, Silva Filho et al., 2023] concerns the manipulation of the confidence scores produced by a classifier so that these effectively reflect the likelihood that a given instance is positive. Quantification [Gonz alez et al., 2017, Esuli et al., 2023] is instead concerned with estimating the prevalence of the classes of interest in an unlabelled set. Finally, classifier accuracy prediction aims at inferring how well a classifier will fare on unseen data [Elsahar and Gall e, 2019, Guillory et al., 2021]. Well-established procedures for attaining these three goals when the IID assumption holds are known and routinely used. For instance, calibrating the classifier's outputs can be attained by learning a calibration map (a function mapping classifier confidence scores into values reflecting the likelihood of the positive class) on held-out validation data [Platt, 2000, Zadrozny and Elkan, 2001a, Barlow and Brunk, 1972].

Population-population generalization is a challenging problem in multi-agent reinforcement learning (MARL), particularly when agents encounter unseen co-players. However, existing self-play-based methods are constrained by the limitation of inside-space generalization. In this study, we propose Bidirectional Distillation (BiDist), a novel mixed-play framework, to overcome this limitation in MARL. BiDist leverages knowledge distillation in two alternating directions: forward distillation, which emulates the historical policies' space and creates an implicit self-play, and reverse distillation, which systematically drives agents towards novel distributions outside the known policy space in a non-self-play manner. In addition, BiDist operates as a concise and efficient solution without the need for the complex and costly storage of past policies. We provide both theoretical analysis and empirical evidence to support BiDist's effectiveness. Our results highlight its remarkable generalization ability across a variety of cooperative, competitive, and social dilemma tasks, and reveal that BiDist significantly diversifies the policy distribution space. We also present comprehensive ablation studies to reinforce BiDist's effectiveness and key success factors. Source codes are available in the supplementary material.

One of the primary challenges in urban autonomous vehicle decision-making and planning lies in effectively managing intricate interactions with diverse traffic participants characterized by unpredictable movement patterns. Additionally, interpreting and adhering to traffic regulations within rapidly evolving traffic scenarios pose significant hurdles. This paper proposed a rule-based autonomous vehicle decision-making and planning framework which extracts right-of-way from traffic rules to generate behavioural parameters, integrating them to effectively adhere to and navigate through traffic regulations. The framework considers the strong interaction between traffic participants mathematically by formulating the decision-making and planning problem into a differential game. By finding the Nash equilibrium of the problem, the autonomous vehicle is able to find optimal decisions. The proposed framework was tested under simulation as well as full-size vehicle platform, the results show that the ego vehicle is able to safely interact with surrounding traffic participants while adhering to traffic rules.

This report explores the speculative question: what if current or future AI systems have qualia, such as pain or pleasure? It does so by assuming that AI systems might someday possess qualia -- and that the quality of these subjective experiences should be considered alongside performance metrics. Concrete mathematical problem settings, inspired by reinforcement learning formulations and theories from philosophy of mind, are then proposed and initial approaches and properties are presented. These properties enable refinement of the problem setting, culminating with the proposal of methods that promote reinforcement.

We introduce NeuralSurv, the first deep survival model to incorporate Bayesian uncertainty quantification. Our non-parametric, architecture-agnostic framework flexibly captures time-varying covariate-risk relationships in continuous time via a novel two-stage data-augmentation scheme, for which we establish theoretical guarantees. For efficient posterior inference, we introduce a mean-field variational algorithm with coordinate-ascent updates that scale linearly in model size. By locally linearizing the Bayesian neural network, we obtain full conjugacy and derive all coordinate updates in closed form. In experiments, NeuralSurv delivers superior calibration compared to state-of-the-art deep survival models, while matching or exceeding their discriminative performance across both synthetic benchmarks and real-world datasets. Our results demonstrate the value of Bayesian principles in data-scarce regimes by enhancing model calibration and providing robust, well-calibrated uncertainty estimates for the survival function.

Sparse linear regression is a fundamental tool in data analysis. However, traditional approaches often fall short when covariates exhibit structure or arise from heterogeneous sources. In biomedical applications, covariates may stem from distinct modalities or be structured according to an underlying graph. We introduce Neural Adaptive Shrinkage (Nash), a unified framework that integrates covariate-specific side information into sparse regression via neural networks. Nash adaptively modulates penalties on a per-covariate basis, learning to tailor regularization without cross-validation. We develop a variational inference algorithm for efficient training and establish connections to empirical Bayes regression. Experiments on real data demonstrate that Nash can improve accuracy and adaptability over existing methods.

In this paper, we consider a score-based Integer Programming (IP) approach for solving the Bayesian Network Structure Learning (BNSL) problem. State-of-the-art BNSL IP formulations suffer from the exponentially large number of variables and constraints. A standard approach in IP to address such challenges is to employ row and column generation techniques, which dynamically generate rows and columns, while the complex pricing problem remains a computational bottleneck for BNSL. For the general class of $\ell_0$-penalized likelihood scores, we show how the pricing problem can be reformulated as a difference of submodular optimization problem, and how the Difference of Convex Algorithm (DCA) can be applied as an inexact method to efficiently solve the pricing problems. Empirically, we show that, for continuous Gaussian data, our row and column generation approach yields solutions with higher quality than state-of-the-art score-based approaches, especially when the graph density increases, and achieves comparable performance against benchmark constraint-based and hybrid approaches, even when the graph size increases.

Gaussian processes (GPs) have gained popularity as flexible machine learning models for regression and function approximation with an in-built method for uncertainty quantification. However, GPs suffer when the amount of training data is large or when the underlying function contains multi-scale features that are difficult to represent by a stationary kernel. To address the former, training of GPs with large-scale data is often performed through inducing point approximations (also known as sparse GP regression (GPR)), where the size of the covariance matrices in GPR is reduced considerably through a greedy search on the data set. To aid the latter, deep GPs have gained traction as hierarchical models that resolve multi-scale features by combining multiple GPs. Posterior inference in deep GPs requires a sampling or, more usual, a variational approximation. Variational approximations lead to large-scale stochastic, non-convex optimisation problems and the resulting approximation tends to represent uncertainty incorrectly. In this work, we combine variational learning with MCMC to develop a particle-based expectation-maximisation method to simultaneously find inducing points within the large-scale data (variationally) and accurately train the GPs (sampling-based). The result is a highly efficient and accurate methodology for deep GP training on large-scale data. We test our method on standard benchmark problems.