Aggregate Reinforcement Learning for multi-agent territory division: The Hide-and-Seek game

Reinforcement Learning (RL) is a successful and established Artificial Intelligence (AI) method, particularly with recent groundbreaking progress in Deep Reinforcement Learning (DRL). Reinforcement learning is very well suited for sequential decision-making tasks, wherein a learned agent learns an optimal policy after many interactions with an environment. The present paper examines the application of reinforcement learning for automating screening of literature in academic research, particularly in the fields of computer science and e-learning. Keyword filtering techniques, while predominantly applied, are found to be inflexible as well as unable to capture the dynamic nature of research themes. To overcome such constraints, we present a Deep Q-Network (DQN)-based reinforcement learning model that combines reinforcement learning with the Semantic Scholar API to enhance research paper classification based on dynamically acquired decision rules. The proposed reinforcement learning model was trained and tested with a dataset of 8,934 research papers, accessed by systematic searching. The agent filtered and picked 11 effective papers depending on improved selection criteria like publication date, keyword relevance, and scholarly topic provided. The model iteratively optimizes the decision-making process through reward-based learning and therefore maximizes categorization accuracy over time. Test experiments demonstrate utilization of RL-based suggested framework yields classification accuracy at 91.5%, recall at 86.3%, and precision at 89.7%. A comparison test demonstrates that the approach performs 12.5% better on recall and 9.8% better on accuracy compared to traditional keyword-filtering methods. The finding confirms the power of the model in minimizing false positives and false negatives for screening literature, hence proving the scalability and adaptability of reinforcement learning in managing high academic data. This work offers a scalable, cognitive approach to conducting systematic reviews of literature through the application of reinforcement learning to programmatically execute work in academic research. The work shows the promise of reinforcement learning to further enhance research methodology, make literature reviews more effective, and facilitate more knowledgeable decision-making in fast-changing scientific disciplines. Further research will be focused on incorporating hybrid AI models with multi-agent systems of reinforcement learning for responsiveness and classification enhancements.

In multi-agent robotic systems, the overlap of actions selected by each agent results in poor cooperation, while, at the same time, conventional reinforcement learning entails a large computational cost because every agent must learn. In this paper, we propose a novel method to solve these problems. The agent uses a rule set to conduct its behavior. Our system consists of reinforcement learning with an Action Selection Priority Level (ASPL) module and a generalized rules module. Using the ASPL, the reinforcement learning module chooses a proper cooperative behavior while the generalized rule module can accelerate the learning process. By applying the proposed method to robot soccer, the learning process can be accelerated by reducing the search space. The results of simulation and real experiments indicate the effectiveness of the proposed method.

The learning of dialogue strategies in spoken dialogue systems using reinforcement learning is a promising approach to acquire robust dialogue strategies. However, the trade-off between available dialogue data and information in the dialogue state either forces information to be excluded from the state representations or requires large amount of training data. In this paper, we propose to use dynamic state aggregation to efficiently learn dialogue policies using less data. State aggregation reduces the size of the problem to be solved. Experimental results show that the proposed method converges faster and that in case of data sparseness, the proposed method is less sensitive to atypical training examples.

Reinforcement Learning with Foregone Payoff Information in Normal Form Games

Offensive cybersecurity is changing because of AI-enabled automation, especially in penetration testing platforms like Kali Linux. There is little academic research evaluating the comparative performance, operational risks, and governance requirements of various tools, such as multi-agent testers like BreachSeek, Large Language Model (LLM) systems like PentestGPT and RapidPen, and Reinforcement Learning (RL) agents like DeepExploit. In order to close this gap, this study presents unique tests carried out on a simulated 20-node business environment and suggests a unified analytical methodology for assessing AI-assisted penetration testing. We assess RL-based, LLM-based, and hybrid multi-agent systems in terms of accuracy, exploitation speed, false-positive rates, failure modes, and adversarial brittleness using standardized attack chains. Results indicate that LLM-driven orchestrators perform better than RL agents in reconnaissance and decision-making (avg. 4.3 min to shell vs. 7.8 min), although RL agents suffer from sparse-reward inefficiencies and provide more consistent payload selection. In line with the EU AI Act, ISO/IEC 42001, and the NIST AI Risk Management Framework (AI RMF), the study incorporates a structured ethical and governance analysis that highlights vulnerabilities including dual-use misuse pathways, over-automation, and hallucinated exploit paths. This work promotes a research-based framework for safe, responsible adoption in cybersecurity operations and offers a fair, fact-based assessment of AI-powered penetration testing.

It has long been known that in some relatively simple reinforcement learning tasks traditional strength-based classifier systems will adapt poorly and show poor generalisation. In contrast, the more recent accuracy-based XCS, appears both to adapt and generalise well. In this work, we attribute the difference to what we call strong over general and fit over general rules. We begin by developing a taxonomy of rule types and considering the conditions under which they may occur. In order to do so an extreme simplification of the classifier system is made, which forces us toward qualitative rather than quantitative analysis. We begin with the basics, considering definitions for correct and incorrect actions, and then correct, incorrect, and overgeneral rules for both strength and accuracy-based fitness. The concept of strong overgeneral rules, which we claim are the Achilles' heel of strength-based classifier systems, are then analysed. It is shown that strong overgenerals depend on what we call biases in the reward function (or, in sequential tasks, the value function). We distinguish between strong and fit overgeneral rules, and show that although strong overgenerals are fit in a strength-based system called SB-XCS, they are not in XCS. Next we show how to design fit overgeneral rules for XCS (but not SB-XCS), by introducing biases in the variance of the reward function, and thus that each system has its own weakness. Finally, we give some consideration to the prevalence of reward and variance function bias, and note that non-trivial sequential tasks have highly biased value functions.

In this paper, a simplified reinforcement learning (RL) of identifier-actor-critic architecture is proposed to solve the formation problem of multiagent state-delay system. The dynamics of multi-agent systems includes the uncertainties and state delay, which is more practical in applications. In the multiagent system formation control, the system uncertainties are counteracted through the fuzzy logic system; the state delay is offset by applying a Lyapunov-Krasovskii functional. The updating laws of RL are derived from a simple equation, which is equivalent to the gradient of the HJB equation. Finally, a simulation example is given to demonstrate the satisfactory performance of the proposed method.

This paper deals with the optimal bipartite consensus control (OBCC) for heterogeneous multi-agent systems (MASs) with time-delay based on reinforcement learning (RL) scheme. MASs, denoted by communication network, is modeled as a signed graph, and the competitive (cooperative) relationship is represented by negative (positive) edges. Firstly, Heterogeneous MASs is depicted by cooperative and competitive (hereinafter referred to as coopetition) network, and local neighborhood bipartite consensus errors and their performance index function (PIF) are put forward to formulate OBCC problem. Secondly, a proper model reduction method is developed to tackle time-delay in coopetition network, and then MASs with time-delay can be transformed into a delay-free MASs. Thirdly, a RL algorithm is employed to solve the solution of Hamilton-Jacobi-Bellman (HJB) equations under OBCC laws, and substantially we adopt neural networks (NNs) to calculate the control policy and PIF online. Finally, the pivotal simulation validates availability of proposed algorithm.

A reinforcement learning and predictive analytics approach for enhancing credit assessment in manufacturing

Despite the significant advancements in single-agent evolutionary reinforcement learning, research exploring evolutionary reinforcement learning within multi-agent systems is still in its nascent stage. The integration of evolutionary algorithms (EA) and reinforcement learning (RL) has partially mitigated RL's reliance on the environment and provided it with an ample supply of data. Nonetheless, existing studies primarily focus on the indirect collaboration between RL and EA, which lacks sufficient exploration on the effective balance of individual and team rewards. To address this problem, this study introduces game theory to establish a dynamic cooperation framework between EA and RL, and proposes a multi-agent evolutionary reinforcement learning based on cooperative games. This framework facilitates more efficient direct collaboration between RL and EA, enhancing individual rewards while ensuring the attainment of team objectives. Initially, a cooperative policy is formed through a joint network to simplify the parameters of each agent to speed up the overall training process. Subsequently, RL and EA engage in cooperative games to determine whether RL jointly optimizes the same policy based on Pareto optimal results. Lastly, through double objectives optimization, a balance between the two types of rewards is achieved, with EA focusing on team rewards and RL focusing on individual rewards. Experimental results demonstrate that the proposed algorithm outperforms its single-algorithm counterparts in terms of competitiveness.

Autonomous Portfolio and Derivatives Risk Management AI Agents: Risk-Aware Reinforcement Learning, Multi-Objective Optimization, and Explainable Allocation Decisions

Q-learning solution for optimal consensus control of discrete-time multiagent systems using reinforcement learning

In this paper, a model-free reinforcement learning (RL) based distributed control protocol for leader-follower multi-agent systems is presented. Despite successful utilization of RL for learning optimal control protocols in multi-agent systems, the effects of the adversarial inputs are neglected in existing results. The susceptibility of the standard synchronization control protocol against adversarial inputs is shown. Then, a RL-based distributed control framework is developed for multi-agent systems to stop corrupted data of a compromised agent from propagating across the network. To this end, only the leader communicates its actual sensory information and other agents estimate the leader state using a distributed observer and communicate this estimation to their neighbors to reach consensus on the leader state. The observer cannot be physically changed by any adversarial input. Therefore, it guarantees that all intact agents synchronize to the leader trajectory except compromised agent. A distributed control protocol is used to further enhance the resiliency by attenuating the effect of the adversarial inputs on the compromised agent itself. An off-policy RL algorithm is developed to solve the output synchronization control problem online and using only measured data along the system trajectories.

The article proposes an optimized leader-follower formation control using a simplified reinforcement learning (RL) of identifier-critic-actor architecture for a class of nonlinear multiagent systems. In general, optimal control is expected to be obtained by solving Hamilton-Jacobi-Bellman (HJB) equation, but the equation associated with a nonlinear system is difficult to solve by analytical method. Although the difficulty can be effectively overcome by the RL strategy, the existing RL algorithms are very complex because their updating laws are obtained by carrying out gradient descent algorithm to square of the approximated HJB equation (Bellman residual error). For a multiagent system, due to the state coupling problem, these methods will become difficult implementation. In the proposed optimized scheme, the RL updating laws are derived from negative gradient of a simple positive function, which is the equivalence to HJB equation; therefore, the control algorithm is significantly simple. Furthermore, in order to solve the problem of unknown system dynamics, an adaptive identifier is integrated into the control. Finally, the theory and simulation demonstrate that the optimized formation scheme can guarantee the desired control performance.

This article addresses the optimal containment fault-tolerant resilient control issues in nonlinear strict feedback multi-agent system (MAS) under unknown fault disturbance. First, human operator interacted with each agent in the MAS. The agent’s control input is a combination of the human operator’s commands, which are not accessible to other agents. To ensure the fault-tolerant cooperative operation of MAS, a networked-based fault interference estimator is developed to observe fault online. In addition, the optimized control design utilizes an actor-critic architecture to approximate Hamilton–Jacobi–Bellman equation for MAS with nonlinear strict-feedback dynamics to realize optimal containment fault-tolerant control. Finally, the proposed optimal algorithm for MAS containment is validated through numerical simulations and practical multiple unmanned aerial vehicles systems (UAV). The proposed algorithm is named human-in-the-loop reinforcement learning with backstepping (HiRLBC). The results demonstrate rapid convergence, with the tracking error approaching near zero, ensuring containment control despite unknown time-varying disturbances. Simultaneously, additional comparative experiments offer further proof of the proposed algorithm’s effectiveness.