In key real-world problems, full state information is sometimes available but only at a high cost, like activating precise yet energy-intensive sensors or consulting humans, thereby compelling the agent to operate under partial observability. For this scenario, we propose AEMS-SR (Anytime Error Minimization Search with State Requests), a principled online planning algorithm tailored for POMDPs with state requests. By representing the search space as a graph instead of a tree, AEMS-SR avoids the exponential growth of the search space originating from state requests. Theoretical analysis demonstrates AEMS-SR's $\varepsilon$-optimality, ensuring solution quality, while empirical evaluations illustrate its effectiveness compared with AEMS and POMCP, two SOTA online planning algorithms. AEMS-SR enables efficient planning in domains characterized by partial observability and costly state requests offering practical benefits across various applications.

We consider the automatic online synthesis of black-box test cases from functional requirements specified as automata for reactive implementations. The goal of the tester is to reach some given state, so as to satisfy a coverage criterion, while monitoring the violation of the requirements. We develop an approach based on Monte Carlo Tree Search, which is a classical technique in reinforcement learning for efficiently selecting promising inputs. Seeing the automata requirements as a game between the implementation and the tester, we develop a heuristic by biasing the search towards inputs that are promising in this game. We experimentally show that our heuristic accelerates the convergence of the Monte Carlo Tree Search algorithm, thus improving the performance of testing.

However, their code-writing abilities are often limited in scope: while they can successfully implement simple functions, they struggle with more complex tasks. A fundamental difference with how an LLM writes code, compared to a human programmer, is that it cannot consistently spot and fix bugs. Debugging is a crucial skill for programmers and it enables iterative code refinement towards a correct implementation. In this work, we propose a novel algorithm to enable LLMs to debug their code via self-reflection and search where a model attempts to identify its previous mistakes. Our key contributions are 1) a best-first tree search algorithm with self-reflections (BESTER) that achieves state-of-the-art Pass@1 in three code generation benchmarks. BESTER maintains its superiority when we measure pass rates taking into account additional inference costs incurred by tree search.

We consider the following problem in computational geometry: given, in the d-dimensional real space, a set of points marked as positive and a set of points marked as negative, such that the convex hull of the positive set does not intersect the negative set, find K hyperplanes that separate, if possible, all the positive points from the negative ones. That is, we search for a convex polyhedron with at most K faces, containing all the positive points and no negative point. The problem is known in the literature for pure convex polyhedral approximation; our interest stems from its possible applications in constraint learning, where points are feasible or infeasible solutions of a Mixed Integer Program, and the K hyperplanes are linear constraints to be found. We cast the problem as an optimization one, minimizing the number of negative points inside the convex polyhedron, whenever exact separation cannot be achieved. We introduce models inspired by support vector machines and we design two mathematical programming formulations with binary variables. We exploit Dantzig-Wolfe decomposition to obtain extended formulations, and we devise column generation algorithms with ad-hoc pricing routines. We compare computing time and separation error values obtained by all our approaches on synthetic datasets, with number of points from hundreds up to a few thousands, showing our approaches to perform better than existing ones from the literature. Furthermore, we observe that key computational differences arise, depending on whether the budget K is sufficient to completely separate the positive points from the negative ones or not. On 8-dimensional instances (and over), existing convex hull algorithms become computational inapplicable, while our algorithms allow to identify good convex hull approximations in minutes of computation.

The constructive approach within Neural Combinatorial Optimization (NCO) treats a combinatorial optimization problem as a finite Markov decision process, where solutions are built incrementally through a sequence of decisions guided by a neural policy network. To train the policy, recent research is shifting toward a 'self-improved' learning methodology that addresses the limitations of reinforcement learning and supervised approaches. Here, the policy is iteratively trained in a supervised manner, with solutions derived from the current policy serving as pseudo-labels. The way these solutions are obtained from the policy determines the quality of the pseudo-labels. In this paper, we present a simple and problem-independent sequence decoding method for self-improved learning based on sampling sequences without replacement. We incrementally follow the best solution found and repeat the sampling process from intermediate partial solutions. By modifying the policy to ignore previously sampled sequences, we force it to consider only unseen alternatives, thereby increasing solution diversity. Experimental results for the Traveling Salesman and Capacitated Vehicle Routing Problem demonstrate its strong performance. Furthermore, our method outperforms previous NCO approaches on the Job Shop Scheduling Problem.

A recent stream of structured learning approaches has improved the practical state of the art for a range of combinatorial optimization problems with complex objectives encountered in operations research. Such approaches train policies that chain a statistical model with a surrogate combinatorial optimization oracle to map any instance of the problem to a feasible solution. The key idea is to exploit the statistical distribution over instances instead of dealing with instances separately. However learning such policies by risk minimization is challenging because the empirical risk is piecewise constant in the parameters, and few theoretical guarantees have been provided so far. In this article, we investigate methods that smooth the risk by perturbing the policy, which eases optimization and improves generalization. Our main contribution is a generalization bound that controls the perturbation bias, the statistical learning error, and the optimization error. Our analysis relies on the introduction of a uniform weak property, which captures and quantifies the interplay of the statistical model and the surrogate combinatorial optimization oracle. This property holds under mild assumptions on the statistical model, the surrogate optimization, and the instance data distribution. We illustrate the result on a range of applications such as stochastic vehicle scheduling. In particular, such policies are relevant for contextual stochastic optimization and our results cover this case.

We present a novel algorithm that fuses the existing convex-programming based approach with heuristic information to find optimality guarantees and near-optimal paths for the Shortest Path Problem in the Graph of Convex Sets (SPP-GCS). Our method, inspired by $A^*$, initiates a best-first-like procedure from a designated subset of vertices and iteratively expands it until further growth is neither possible nor beneficial. Traditionally, obtaining solutions with bounds for an optimization problem involves solving a relaxation, modifying the relaxed solution to a feasible one, and then comparing the two solutions to establish bounds. However, for SPP-GCS, we demonstrate that reversing this process can be more advantageous, especially with Euclidean travel costs. In other words, we initially employ $A^*$ to find a feasible solution for SPP-GCS, then solve a convex relaxation restricted to the vertices explored by $A^*$ to obtain a relaxed solution, and finally, compare the solutions to derive bounds. We present numerical results to highlight the advantages of our algorithm over the existing approach in terms of the sizes of the convex programs solved and computation time.

Abstract--Autonomously tailoring content to a set of predetermined affective patterns has long been considered the holy grail of affect-aware human-computer interaction at large. In this paper, we propose a novel reinforcement learning (RL) framework for generating affecttailored content, and we test it in the domain of racing games. Specifically, the experience-driven RL (EDRL) framework is given a target arousal trace, and it then generates a racetrack that elicits the desired affective responses for a particular type of player. EDRL leverages a reward function that assesses the affective pattern of any generated racetrack from a corpus of arousal traces. Our findings suggest that EDRL can accurately generate affect-driven racing game levels according to a designer's style and outperforms search-based methods for personalised content generation. The method is not only directly applicable to game content generation tasks but also employable broadly to any domain that uses content for affective adaptation. Two examples of maximally and minimally arousing tracks generated by EDRL for the Solid Rally racing game.

A $k$-defective clique of an undirected graph $G$ is a subset of its vertices that induces a nearly complete graph with a maximum of $k$ missing edges. The maximum $k$-defective clique problem, which asks for the largest $k$-defective clique from the given graph, is important in many applications, such as social and biological network analysis. In the paper, we propose a new branching algorithm that takes advantage of the structural properties of the $k$-defective clique and uses the efficient maximum clique algorithm as a subroutine. As a result, the algorithm has a better asymptotic running time than the existing ones. We also investigate upper-bounding techniques and propose a new upper bound utilizing the \textit{conflict relationship} between vertex pairs. Because conflict relationship is common in many graph problems, we believe that this technique can be potentially generalized. Finally, experiments show that our algorithm outperforms state-of-the-art solvers on a wide range of open benchmarks.

Combinatorial optimization (CO) problems are crucial in various scientific and industrial applications. Recently, researchers have proposed using unsupervised Graph Neural Networks (GNNs) to address NP-hard combinatorial optimization problems, which can be reformulated as Quadratic Unconstrained Binary Optimization (QUBO) problems. GNNs have demonstrated high performance with nearly linear scalability and significantly outperformed classic heuristic-based algorithms in terms of computational efficiency on large-scale problems. However, when utilizing standard node features, GNNs tend to get trapped to suboptimal local minima of the energy landscape, resulting in low quality solutions. We introduce a novel algorithm, denoted hereafter as QRF-GNN, leveraging the power of GNNs to efficiently solve CO problems with QUBO formulation. It relies on unsupervised learning by minimizing the loss function derived from QUBO relaxation. The proposed key components of the architecture include the recurrent use of intermediate GNN predictions, parallel convolutional layers and combination of static node features as input. Altogether, it helps to adapt the intermediate solution candidate to minimize QUBO-based loss function, taking into account not only static graph features, but also intermediate predictions treated as dynamic, i.e. iteratively changing recurrent features. The performance of the proposed algorithm has been evaluated on the canonical benchmark datasets for maximum cut, graph coloring and maximum independent set problems. Results of experiments show that QRF-GNN drastically surpasses existing learning-based approaches and is comparable to the state-of-the-art conventional heuristics, improving their scalability on large instances.