Abstract
Nim is a mathematical combinatorial game in which two players take turns removing, or nimming, objects from distinct heaps or piles Although its rules are simple, which makes it extremely easy to play, it requires a solid strategic reasoning in order to win against experienced players. This study presents an optimised strategic approach to the game of Nim, which represents the guaranteed winning strategy for this game for the first player to take action. The proposed approach is a fundamental combinatorial game rooted in Boolean algebra and the XOR operation. Unlike traditional strategies that solely rely on XOR calculations to determine winning and losing positions, this research identifies and analyses anomalous strategic behaviours that challenge conventional Nim theory, revealing previously unexplored patterns in specific game configurations. To validate these findings, a Python-based application has been developed, implementing the proposed strategy to ensure consistent victory. The algorithm systematically applies XOR calculations, executes optimal moves, and dynamically adapts to anomalies, demonstrating how these irregularities can be leveraged for strategic advantage. This computational validation reinforces the theoretical framework and provides new insights into the limitations and extensions of classical Nim strategies. Beyond its implications for Nim, this research highlights the broader potential of AI-driven decision-making in combinatorial games. By demonstrating how algorithmic intelligence can analyse game states, predict outcomes, and refine strategies, this study contributes to advancements in artificial intelligence, optimisation algorithms, and complex strategic decision-making models.

Abstract
This chapter explores the potential of thermal energy storage (TES) systems towards the decarbonization of industry and energy networks, considering its coordinated management with electrochemical energy storage and renewable energy sources (RES). It covers various TES technologies, including sensible heat storage (SHS), latent heat storage (LHS), and thermochemical energy storage (TCS), each offering unique benefits and facing specific challenges. The integration of TES into industrial parks is highlighted, showing how these systems can optimize energy manage-ment and reduce reliance on external sources. A district heating use case also demonstrates the economic and environmental advantages of a multi-energy management strategy over single-energy approaches. Overall, TES technologies are presented as a promising pathway to greater energy effi-ciency and sustainability in industrial processes.

Abstract
Handling imbalanced target distributions in regression poses a persistent challenge, as the underrepresentation of relevant target values can significantly hinder model performance. Existing data-level solutions often adapt classification-oriented techniques, introducing arbitrary thresholds over the continuous target and leading to artificial and potentially misleading problem formulations. Deep generative models offer flexible sample synthesis but are computationally intensive and difficult to interpret. We propose a CART-based synthetic sampling method specifically designed for imbalanced regression on tabular data. The method integrates relevance- and density-guided sampling to address sparse target regions without thresholding, and employs a feature-driven tree structure to generate realistic tabular samples across heterogeneous features and non-linear interactions. Experiments on benchmark datasets for extreme-value prediction show that the proposed approach is competitive with state-of-the-art resampling and generative methods while offering faster execution and greater transparency. These results highlight its potential as a scalable and interpretable data-level strategy for improving regression models in imbalanced domains. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Abstract
Forest management and operations planning involve complex decisions that integrate ecological knowledge, spatial data, and analytical tools to balance sustainable resource use with risk mitigation. Disturbances such as storms, diseases, and wildfires increasingly disrupt forest ecosystems and value chains. The timely removal, processing, and delivery of forest residues to bioenergy facilities are essential to reduce wildfire risk, prevent disease spread, and ensure operational continuity for forest managers and owners. This study presents a decision-support approach to address supply uncertainty caused by wildfires within the forest-to-bioenergy value chain. The methodology first generates multiple raw material variability scenarios using a fire simulation model, then clusters them according to post-fire biomass availability and probability of occurrence. These clusters are integrated into a two-stage stochastic optimization model incorporating a Conditional Value-at-Risk (CVaR) metric. Results show that the stochastic model with CVaR achieves the lowest total cost while ensuring complete processing of biomass under the most severe wildfire scenarios. The findings highlight the value of flexible and risk-aware planning strategies for forest operations, supporting decision-makers in balancing investments in processing capacity, cost efficiency, and post-disturbance resource utilization.

Abstract

Abstract
Reinforcement learning (RL) provides a principled framework for decision-making in partially observable environments, which can be modeled as Markov decision processes and compactly represented through dynamic decision Bayesian networks. Recent advances demonstrate that inference on sparse Bayesian networks can be accelerated using quantum rejection sampling combined with amplitude amplification, leading to a computational speedup in estimating acceptance probabilities. Building on this result, we introduce Quantum Bayesian Reinforcement Learning (QBRL), a hybrid quantum-classical look-ahead algorithm for model-based RL in partially observable environments. We present a rigorous, oracle-free time complexity analysis under fault-tolerant assumptions for the quantum device. Unlike standard treatments that assume a black-box oracle, we explicitly specify the inference process, allowing our bounds to more accurately reflect the true computational cost. We show that, for environments whose dynamics form a sparse Bayesian network, horizon-based near-optimal planning can be achieved sub-quadratically faster through quantum-enhanced belief updates. On the other hand, we show that there is no quantum speed-up for environments that are either fully observable, or characterized by Bayesian networks whose maximum in-degree is not small. Furthermore, we present numerical experiments benchmarking QBRL against its classical counterpart on simple yet illustrative decision-making tasks. Our results offer a detailed analysis of how the quantum computational advantage translates into decision-making performance, highlighting that the magnitude of the advantage can vary significantly across different deployment settings.