Guiding Multi-agent Multi-task Reinforcement Learning by a Hierarchical Framework with Logical Reward Shaping

Multi-agent hierarchical reinforcement learning (MAHRL) has been studied as an effective means to solve intelligent decision problems in complex and large-scale environments. However, most current MAHRL algorithms follow the traditional way of using reward functions in reinforcement learning, which limits their use to a single task. This study aims to design a multi-agent cooperative algorithm with logic reward shaping (LRS), which uses a more flexible way of setting the rewards, allowing for the effective completion of multi-tasks. LRS uses Linear Temporal Logic (LTL) to express the internal logic relation of subtasks within a complex task. Then, it evaluates whether the subformulae of the LTL expressions are satisfied based on a designed reward structure. This helps agents to learn to effectively complete tasks by adhering to the LTL expressions, thus enhancing the interpretability and credibility of their decisions. To enhance coordination and cooperation among multiple agents, a value iteration technique is designed to evaluate the actions taken by each agent. Based on this evaluation, a reward function is shaped for coordination, which enables each agent to evaluate its status and complete the remaining subtasks through experiential learning. Experiments have been conducted on various types of tasks in the Minecraft-like environment. The results demonstrate that the proposed algorithm can improve the performance of multi-agents when learning to complete multi-tasks.

DFDRNN: A dual-feature based neural network for drug repositioning

Drug repositioning is an economically efficient strategy used to discover new indications for existing drugs beyond their original approvals, expanding their applicability and usage to address challenges in disease treatment. In recent years, deep-learning techniques for drug repositioning have gained much attention. While most deep learning-based research methods focus on encoding drugs and diseases by extracting feature information from neighbors in the network, they often pay little attention to the potential relationships between the features of drugs and diseases, leading to imprecise encoding of drugs and diseases. To address this, we design a dual-feature drug repositioning neural network (DFDRNN) model to achieve precise encoding of drugs and diseases. DFDRNN uses two features to represent drugs and diseases: the similarity feature and the association feature. The model incorporates a self-attention mechanism to design two dual-feature extraction modules for achieving precisely encoding of drugs and diseases: the intra-domain dual-feature extraction (IntraDDFE) module and the inter-domain dual-feature extraction (InterDDFE) module. The IntraDDFE module extracts features from a single domain (drug or disease domain), while the InterDDFE module extracts features from the mixed domain (drug and disease domain). In particular, the feature is changed by InterDDFE, ensuring a precise encoding of drugs and diseases. Finally, a cross-dual-domain decoder is designed to predict drug-disease associations in both the drug and disease domains. Compared to six state-of-the-art methods, DFDRNN outperforms others on four benchmark datasets, with an average AUROC of 0.946 and an average AUPR of 0.597.

Improving Critical Node Detection Using Neural Network-based Initialization in a Genetic Algorithm

The Critical Node Problem (CNP) is concerned with identifying the critical nodes in a complex network. These nodes play a significant role in maintaining the connectivity of the network, and removing them can negatively impact network performance. CNP has been studied extensively due to its numerous real-world applications. Among the different versions of CNP, CNP-1a has gained the most popularity. The primary objective of CNP-1a is to minimize the pair-wise connectivity in the remaining network after deleting a limited number of nodes from a network. Due to the NP-hard nature of CNP-1a, many heuristic/metaheuristic algorithms have been proposed to solve this problem. However, most existing algorithms start with a random initialization, leading to a high cost of obtaining an optimal solution. To improve the efficiency of solving CNP-1a, a knowledge-guided genetic algorithm named K2GA has been proposed. Unlike the standard genetic algorithm framework, K2GA has two main components: a pretrained neural network to obtain prior knowledge on possible critical nodes, and a hybrid genetic algorithm with local search for finding an optimal set of critical nodes based on the knowledge given by the trained neural network. The local search process utilizes a cut node-based greedy strategy. The effectiveness of the proposed knowledgeguided genetic algorithm is verified by experiments on 26 realworld instances of complex networks. Experimental results show that K2GA outperforms the state-of-the-art algorithms regarding the best, median, and average objective values, and improves the best upper bounds on the best objective values for eight realworld instances.

A Dual-mode Local Search Algorithm for Solving the Minimum Dominating Set Problem

Given a graph, the minimum dominating set (MinDS) problem is to identify a smallest set $D$ of vertices such that every vertex not in $D$ is adjacent to at least one vertex in $D$. The MinDS problem is a classic $\mathcal{NP}$-hard problem and has been extensively studied because of its many disparate applications in network analysis. To solve this problem efficiently, many heuristic approaches have been proposed to obtain a good solution within an acceptable time limit. However, existing MinDS heuristic algorithms are always limited by various tie-breaking cases when selecting vertices, which slows down the effectiveness of the algorithms. In this paper, we design an efficient local search algorithm for the MinDS problem, named DmDS -- a dual-mode local search framework that probabilistically chooses between two distinct vertex-swapping schemes. We further address limitations of other algorithms by introducing vertex selection criterion based on the frequency of vertices added to solutions to address tie-breaking cases, and a new strategy to improve the quality of the initial solution via a greedy-based strategy integrated with perturbation. We evaluate DmDS against the state-of-the-art algorithms on seven datasets, consisting of 346 instances (or families) with up to tens of millions of vertices. Experimental results show that DmDS obtains the best performance in accuracy for almost all instances and finds much better solutions than state-of-the-art MinDS algorithms on a broad range of large real-world graphs.

The Design and Realization of Multi-agent Obstacle Avoidance based on Reinforcement Learning

Intelligence agents and multi-agent systems play important roles in scenes like the control system of grouped drones, and multi-agent navigation and obstacle avoidance which is the foundational function of advanced application has great importance. In multi-agent navigation and obstacle avoidance tasks, the decision-making interactions and dynamic changes of agents are difficult for traditional route planning algorithms or reinforcement learning algorithms with the increased complexity of the environment. The classical multi-agent reinforcement learning algorithm, Multi-agent deep deterministic policy gradient(MADDPG), solved precedent algorithms' problems of having unstationary training process and unable to deal with environment randomness. However, MADDPG ignored the temporal message hidden beneath agents' interaction with the environment. Besides, due to its CTDE technique which let each agent's critic network to calculate over all agents' action and the whole environment information, it lacks ability to scale to larger amount of agents. To deal with MADDPG's ignorance of the temporal information of the data, this article proposes a new algorithm called MADDPG-LSTMactor, which combines MADDPG with Long short term memory (LSTM). By using agent's observations of continuous timesteps as the input of its policy network, it allows the LSTM layer to process the hidden temporal message. Experimental result demonstrated that this algorithm had better performance in scenarios where the amount of agents is small. Besides, to solve MADDPG's drawback of not being efficient in scenarios where agents are too many, this article puts forward a light-weight MADDPG (MADDPG-L) algorithm, which simplifies the input of critic network. The result of experiments showed that this algorithm had better performance than MADDPG when the amount of agents was large.

An Adaptive Repeated-Intersection-Reduction Local Search for the Maximum Independent Set Problem

The maximum independent set (MIS) problem, a classical NP-hard problem with extensive applications in various areas, aims to find a largest set of vertices with no edge among them. Due to its computational intractability, it is difficult to solve the MIS problem effectively, especially on large graphs. Employing heuristic approaches to obtain a good solution within an acceptable amount of time has attracted much attention in literature. In this paper, we propose an efficient local search algorithm for MIS called ARIR, which consists of two main parts: an adaptive local search framework, and a novel inexact efficient reduction rule to simplify instances. We conduct experiments on five benchmarks, encompassing 92 instances. Compared with four state-of-the-art algorithms, ARIR offers the best accuracy on 89 instances and obtains competitive results on the three remaining instances.

Preference at First Sight

We consider decision-making and game scenarios in which an agent is limited by his/her computational ability to foresee all the available moves towards the future - that is, we study scenarios with short sight. We focus on how short sight affects the logical properties of decision making in multi-agent settings. We start with single-agent sequential decision making (SSDM) processes, modeling them by a new structure of "preference-sight trees". Using this model, we first explore the relation between a new natural solution concept of Sight-Compatible Backward Induction (SCBI) and the histories produced by classical Backward Induction (BI). In particular, we find necessary and sufficient conditions for the two analyses to be equivalent. Next, we study whether larger sight always contributes to better outcomes. Then we develop a simple logical special-purpose language to formally express some key properties of our preference-sight models. Lastly, we show how short-sight SSDM scenarios call for substantial enrichments of existing fixed-point logics that have been developed for the classical BI solution concept. We also discuss changes in earlier modal logics expressing "surface reasoning" about best actions in the presence of short sight. Our analysis may point the way to logical and computational analysis of more realistic game models.