Monte-Carlo Tree Search (MCTS) typically uses multi-armed bandit (MAB) strategies designed to minimize cumulative regret, such as UCB1, as its selection strategy. However, in the root node of the search tree, it is more sensible to minimize simple regret. Previous work has proposed using Sequential Halving as selection strategy in the root node, as, in theory, it performs better with respect to simple regret. However, Sequential Halving requires a budget of iterations to be predetermined, which is often impractical. This paper proposes an anytime version of the algorithm, which can be halted at any arbitrary time and still return a satisfactory result, while being designed such that it approximates the behavior of Sequential Halving. Empirical results in synthetic MAB problems and ten different board games demonstrate that the algorithm's performance is competitive with Sequential Halving and UCB1 (and their analogues in MCTS).

The performance of Variational Quantum Algorithms (VQAs) strongly depends on the choice of the parameterized quantum circuit to optimize. One of the biggest challenges in VQAs is designing quantum circuits tailored to the particular problem. This article proposes a gradient‐free Monte Carlo Tree Search (MCTS) technique to automate the process of quantum circuit design. Our proposed technique introduces a novel formulation of the action space based on a sampling scheme and a progressive widening technique to explore the space dynamically. When testing our MCTS approach on the domain of random quantum circuits, MCTS approximates unstructured circuits under different values of stabilizer Rényi entropy. It turns out that MCTS manages to approximate the benchmark quantum states independently from their degree of nonstabilizerness. Next, our technique exhibits robustness across various application domains, including quantum chemistry and systems of linear equations. Compared to previous MCTS research, our technique reduces the number of quantum circuit evaluations by a factor of 10 up to 100 while achieving equal or better results. In addition, the resulting quantum circuits exhibit up to three times fewer two‐qubit gates, which is important for implementation on noisy quantum hardware.

Foreign-object detection systems based on machine learning perform well when trained on a substantial amount of high-quality data that reflect well the environment in which they will be deployed. In industrial applications, data are often not readily available, and the collection and annotation of data is accompanied by large costs, labour, and time. Moreover, over time, the industrial setting may change, and the previously fine-tuned machine-learning model may not be suitable to the changed setting anymore. We propose a novel active-learning based method for foreign object detection that addresses these problems. Our method strategically selects the samples for automatic labelling or manual annotation on the basis of class-specific accuracy. Moreover, a class-based sampling technique is employed to maintain the class balance to avoid catastrophic forgetting. Experimental results demonstrate that our method achieves comparable accuracy to the model trained with all data with fewer samples, thus reducing cost for labelling, saving time, and lowering computational complexity to retrain.

This paper presents Generalized Proof-Number Monte-Carlo Tree Search: a generalization of recently proposed combinations of Proof-Number Search (PNS) with Monte-Carlo Tree Search (MCTS), which use (dis)proof numbers to bias UCB1-based Selection strategies towards parts of the search that are expected to be easily (dis)proven. We propose three core modifications of prior combinations of PNS with MCTS. First, we track proof numbers per player. This reduces code complexity in the sense that we no longer need disproof numbers, and generalizes the technique to be applicable to games with more than two players. Second, we propose and extensively evaluate different methods of using proof numbers to bias the selection strategy, achieving strong performance with strategies that are simpler to implement and compute. Third, we merge our technique with Score Bounded MCTS, enabling the algorithm to prove and leverage upper and lower bounds on scores - as opposed to only proving wins or not-wins. Experiments demonstrate substantial performance increases, reaching the range of 80% for 8 out of the 11 tested board games.

In the future high-luminosity LHC era, high-energy physics experiments face unprecedented computational challenges for event reconstruction. Employing the LHCb vertex locator as a case study we investigate a novel approach for charged particle track reconstruction. The algorithm hinges on minimizing an Ising-like Hamiltonian using matrix inversion. Solving this matrix inversion classically achieves reconstruction efficiencies akin to current stateof-the-art algorithms. Exploiting the Harrow-Hassidim-Lloyd (HHL) quantum algorithm for linear systems holds the promise of an exponential speedup in the number of input hits over its classical counterpart, contingent on the conditions of efficient quantum phase estimation (QPE) and effectively reading out the algorithm’s output. This contribution builds on previous work by Nicotra et al. [1] and strives to fulfill these conditions and further streamlines the algorithm’s circuit depth by a factor up to 104. Our version of the HHL algorithm restricts the QPE precision to one bit, largely reducing circuit depth and addressing HHL’s readout issue. Furthermore, this allows for the implementation of a post-processing algorithm that reconstructs event Primary Vertices (PVs). The findings presented here aim to further illuminate the potential of harnessing quantum computing for the future of particle track reconstruction in high-energy physics.

This paper proposes a new game-search algorithm, PN-MCTS, which combines Monte-Carlo Tree Search (MCTS) and Proof-Number Search (PNS). These two algorithms have been successfully applied for decision making in a range of domains. We define three areas where the additional knowledge provided by the proof and disproof numbers gathered in MCTS trees might be used: final move selection, solving subtrees, and the UCB1 selection mechanism. We test all possible combinations on different time settings, playing against vanilla UCT on several games: Lines of Action (7×7 and 8×8 board sizes), MiniShogi, Knightthrough, and Awari. Furthermore, we extend this new algorithm to properly address games with draws, like Awari, by adding an additional layer of PNS on top of the MCTS tree. The experiments show that PN-MCTS is able to outperform MCTS in all tested game domains, achieving win rates up to 96.2% for Lines of Action.

It is common practice in reinforcement learning (RL) research to train and deploy agents in bespoke simulators, typically implemented by engineers directly in general-purpose programming languages or hardware acceleration frameworks such as CUDA or JAX. This means that programming and engineering expertise is not only required to develop RL algorithms, but is also required to use already developed algorithms for novel problems. The latter poses a problem in terms of the usability of RL, in particular for private individuals and small organisations without substantial engineering expertise. We also perceive this as a challenge for effective generalisation in RL, in the sense that is no standard, shared formalism in which different problems are represented. As we typically have no consistent representation through which to provide information about any novel problem to an agent, our agents also cannot instantly or rapidly generalise to novel problems. In this position paper, we advocate for a research agenda centred around the use of user-friendly description languages for describing problems, such that (i) users with little to no engineering expertise can formally describe the problems they would like to be tackled by RL algorithms, and (ii) algorithms can leverage problem descriptions to effectively generalise among all problems describable in the language of choice.

Typically, research on Explainable Artificial Intelligence (XAI) focuses on black-box models within the context of a general policy in a known, specific domain. This paper advocates for the need for knowledge-agnostic explainability applied to the subfield of XAI called Explainable Search, which focuses on explaining the choices made by intelligent search techniques. It proposes Monte-Carlo Tree Search (MCTS) enhancements as a solution to obtaining additional data and providing higher-quality explanations while remaining knowledge-free, and analyzes the most popular enhancements in terms of the specific types of explainability they introduce. So far, no other research has considered the explainability of MCTS enhancements. We present a proof-of-concept that demonstrates the advantages of utilizing enhancements.

Many enhancements to Monte-Carlo Tree Search (MCTS) have been proposed over almost two decades of general game playing and other artificial intelligence research. However, our ability to characterise and understand which variants work well or poorly in which games is still lacking. This paper describes work on an initial dataset that we have built to make progress towards such an understanding: 268,386 plays among 61 different agents across 1494 distinct games. We describe a preliminary analysis and work on training predictive models on this dataset, as well as lessons learned and future plans for a new and improved version of the dataset.

Upper Confidence bounds applied to Trees (UCT) is the default selection policy in Monte-Carlo Tree Search (MCTS), yet it overlooks the strategic use of ancestral node information. Consequently, UCT approaches each decision level as an independent Multi-Armed Bandit problem, disregarding the results achieved along the path that led to the current state. Consequently, it treats decisions as separate in the tree, without integrating the historical context of previous choices. This paper introduces an enhancement to UCT for two-player, deterministic zero-sum games by integrating insights from alpha-beta pruning-a method that increases minimax search efficiency through selective pruning. We propose a revised selection policy that leverages ancestor node data, mirroring alpha-beta pruning's principle, to refine sample-based search. Our experiments with this enhanced method reveal performance gains in Breakthrough, Mini Shogi, and GoMoku, highlighting the effectiveness of incorporating ancestor search results into the MCTS selection processes.

The field of Explainable Artificial Intelligence has gained popularity in recent years, due to the need for users to understand AI-made decisions, in order to increase their trust in the AI system. However, not much work has been performed on explaining recommendations made by search algorithms, which do not focus on single decisions, but on complex plans of action. This paper investigates promising directions for research in Explainable Search (XS), by evaluating with a user study different types of explanations for a search-based algorithm. Preliminary results suggest that users prefer explanations generated using context-based features, which are not only based on the current state of the problem, but are extracted from different parts of the tree generated by the search algorithm.

As more AI solutions are implemented in every aspect of our lives, the need for Explainable Artificial Intelligence (XAI) rises. Explanations can have different forms, such as a number (or an equation), a figure, or a text. This paper investigates textual explanations to effectively communicate the reason for a decision made by an AI system. In previous works, linguistic summaries, as an example of a textual explanation, have already been tested and shown to have explanatory potential. In this paper, we explore this topic further and present a roadmap for linguistic summaries to become a proper XAI tool as Explainable Linguistic Summaries (XLSs). We discuss the challenges that an XLS has to overcome. We outline possible solutions and state their consequences. We consider different protoforms, the definition of the membership function, heuristics for the selection of XLS and personalizing the explanations as well as options to gain more insights into the explanations.

report om the results of the 32 events.It is followed by a report of Quentin Cohen-Solal and Tristan Cazenave describing their engine ATHÉNAN, which entered 21 events and earned 21 medals, including 16 times