A major challenge in deploying reinforcement learning in online tasks is ensuring that safety is maintained throughout the learning process. In this work, we propose CERL, a new method for solving constrained Markov decision processes while keeping the policy safe during learning. Our method leverages Bayesian world models and suggests policies that are pessimistic w.r.t. the model's epistemic uncertainty. This makes CERL robust towards model inaccuracies and leads to safe exploration during learning. In our experiments, we demonstrate that CERL outperforms the current state-of-the-art in terms of safety and optimality in solving CMDPs from image observations.

Flamenco, recognized by UNESCO as part of the Intangible Cultural Heritage of Humanity, is a profound expression of cultural identity rooted in Andalusia, Spain. However, there is a lack of quantitative studies that help identify characteristic patterns in this long-lived music tradition. In this work, we present a computational analysis of Flamenco lyrics, employing natural language processing and machine learning to categorize over 2000 lyrics into their respective Flamenco genres, termed as $\textit{palos}$. Using a Multinomial Naive Bayes classifier, we find that lexical variation across styles enables to accurately identify distinct $\textit{palos}$. More importantly, from an automatic method of word usage, we obtain the semantic fields that characterize each style. Further, applying a metric that quantifies the inter-genre distance we perform a network analysis that sheds light on the relationship between Flamenco styles. Remarkably, our results suggest historical connections and $\textit{palo}$ evolutions. Overall, our work illuminates the intricate relationships and cultural significance embedded within Flamenco lyrics, complementing previous qualitative discussions with quantitative analyses and sparking new discussions on the origin and development of traditional music genres.

In this study, we introduce a novel shared-control system for key-hole docking operations, combining a commercial camera with occlusion-robust pose estimation and a hand-eye information fusion technique. This system is used to enhance docking precision and force-compliance safety. To train a hand-eye information fusion network model, we generated a self-supervised dataset using this docking system. After training, our pose estimation method showed improved accuracy compared to traditional methods, including observation-only approaches, hand-eye calibration, and conventional state estimation filters. In real-world phantom experiments, our approach demonstrated its effectiveness with reduced position dispersion (1.23\pm 0.81 mm vs. 2.47 \pm 1.22 mm) and force dispersion (0.78\pm 0.57 N vs. 1.15 \pm 0.97 N) compared to the control group. These advancements in semi-autonomy co-manipulation scenarios enhance interaction and stability. The study presents an anti-interference, steady, and precision solution with potential applications extending beyond laparoscopic surgery to other minimally invasive procedures.

We present an A*-based algorithm to compute policies for finite-horizon Dec-POMDPs. Our goal is to sacrifice optimality in favor of scalability for larger horizons. The main ingredients of our approach are (1) using clustered sliding window memory, (2) pruning the A* search tree, and (3) using novel A* heuristics. Our experiments show competitive performance to the state-of-the-art. Moreover, for multiple benchmarks, we achieve superior performance. In addition, we provide an A* algorithm that finds upper bounds for the optimum, tailored towards problems with long horizons. The main ingredient is a new heuristic that periodically reveals the state, thereby limiting the number of reachable beliefs. Our experiments demonstrate the efficacy and scalability of the approach.

Open-ended worlds are those in which there are no pre-specified goals or environmental reward signal. As a consequence, an agent must know how to perform a multitude of tasks. However, when a new task is presented to an agent, we expect it to be able to reuse some of what it knows from previous tasks to rapidly learn that new task. We introduce a novel technique whereby policies for different a priori known tasks are combined into a Mixture-of-Experts model with an attention mechanism across a mix of frozen and unfrozen experts. The model learns when to attend to frozen task-specific experts when appropriate and learns new experts to handle novel situations. We work in an open-ended text-based environment in which the agent is tasked with behaving like different types of character roles and must rapidly learn behaviors associated with new character role types. We show that our agent both obtains more rewards in the zero-shot setting, and discovers these rewards with greater sample efficiency in the few-shot learning settings.

Additive control variates give rise to baseline corrections [16], regression adjustments [15], and doubly robust The off-policy learning paradigm allows for recommender systems estimators [13]. Multiplicative control variates lead to selfnormalised and general ranking applications to be framed as decision-making estimators [32, 59]. Previous work has proven that for problems, where we aim to learn decision policies that optimize off-policy learning tasks, the multiplicative control variates can an unbiased offline estimate of an online reward metric. With unbiasedness be re-framed using an equivalent additive variate [6, 30], enabling comes potentially high variance, and prevalent methods mini-batch optimization methods to be used. We note that the exist to reduce estimation variance. These methods typically make self-normalised estimator is only asymptotically unbiased: a clear use of control variates, either additive (i.e., baseline corrections or disadvantage for evaluation with finite samples. The common problem doubly robust methods) or multiplicative (i.e., self-normalisation). which most existing methods tackle is that of variance reduction Our work unifies these approaches by proposing a single framework in offline value estimation, either for learning or for evaluation. The built on their equivalence in learning scenarios. The foundation common solution is the application of a control variate, either multiplicative of our framework is the derivation of an equivalent baseline or additive [42].

Cross-domain offline reinforcement learning leverages source domain data with diverse transition dynamics to alleviate the data requirement for the target domain. However, simply merging the data of two domains leads to performance degradation due to the dynamics mismatch. Existing methods address this problem by measuring the dynamics gap via domain classifiers while relying on the assumptions of the transferability of paired domains. In this paper, we propose a novel representation-based approach to measure the domain gap, where the representation is learned through a contrastive objective by sampling transitions from different domains. We show that such an objective recovers the mutual-information gap of transition functions in two domains without suffering from the unbounded issue of the dynamics gap in handling significantly different domains. Based on the representations, we introduce a data filtering algorithm that selectively shares transitions from the source domain according to the contrastive score functions. Empirical results on various tasks demonstrate that our method achieves superior performance, using only 10% of the target data to achieve 89.2% of the performance on 100% target dataset with state-of-the-art methods.

We introduce a novel multi-armed bandit framework, where each arm is associated with a fixed unknown credal set over the space of outcomes (which can be richer than just the reward). The arm-to-credal-set correspondence comes from a known class of hypotheses. We then define a notion of regret corresponding to the lower prevision defined by these credal sets. Equivalently, the setting can be regarded as a two-player zero-sum game, where, on each round, the agent chooses an arm and the adversary chooses the distribution over outcomes from a set of options associated with this arm. The regret is defined with respect to the value of game. For certain natural hypothesis classes, loosely analgous to stochastic linear bandits (which are a special case of the resulting setting), we propose an algorithm and prove a corresponding upper bound on regret. We also prove lower bounds on regret for particular special cases.

Industrial prognostics focuses on utilizing degradation signals to forecast and continually update the residual useful life of complex engineering systems. However, existing prognostic models for systems with multiple failure modes face several challenges in real-world applications, including overlapping degradation signals from multiple components, the presence of unlabeled historical data, and the similarity of signals across different failure modes. To tackle these issues, this research introduces two prognostic models that integrate the mixture (log)-location-scale distribution with deep learning. This integration facilitates the modeling of overlapping degradation signals, eliminates the need for explicit failure mode identification, and utilizes deep learning to capture complex nonlinear relationships between degradation signals and residual useful lifetimes. Numerical studies validate the superior performance of these proposed models compared to existing methods.

There have been many applications of deep neural networks to detector calibrations and a growing number of studies that propose deep generative models as automated fast detector simulators. We show that these two tasks can be unified by using maximum likelihood estimation (MLE) from conditional generative models for energy regression. Unlike direct regression techniques, the MLE approach is prior-independent and non-Gaussian resolutions can be determined from the shape of the likelihood near the maximum. Using an ATLAS-like calorimeter simulation, we demonstrate this concept in the context of calorimeter energy calibration.