Performance Of Agents Research Articles

Statistical refinement of patient-centered case vignettes for digital health research.

Digital health research often relies on case vignettes (descriptions of fictitious or real patients) to navigate ethical and practical challenges. Despite their utility, the quality and lack of standardization of these vignettes has often been criticized, especially in studies on symptom-assessment applications (SAAs) and self-triage decision-making. To address this, our paper introduces a method to refine an existing set of vignettes, drawing on principles from classical test theory. First, we removed any vignette with an item difficulty of zero and an item-total correlation below zero. Second, we stratified the remaining vignettes to reflect the natural base rates of symptoms that SAAs are typically approached with, selecting those vignettes with the highest item-total correlation in each quota. Although this two-step procedure reduced the size of the original vignette set by 40%, comparing self-triage performance on the reduced and the original vignette sets, we found a strong correlation (r = 0.747 to r = 0.997, p < .001). This indicates that using our refinement method helps identifying vignettes with high predictive power of an agent's self-triage performance while simultaneously increasing cost-efficiency of vignette-based evaluation studies. This might ultimately lead to higher research quality and more reliable results.

Deep reinforcement learning using deep-Q-network for Global Maximum Power Point tracking: Design and experiments in real photovoltaic systems

This paper presents a methodology for integrating Deep Reinforcement Learning (DRL) using a Deep-Q-Network (DQN) agent into real-time experiments to achieve the Global Maximum Power Point (GMPP) of Photovoltaic (PV) systems under various environmental conditions. Conventional methods, such as the Perturb and Observe (P&O) algorithm, often become stuck at the Local Maximum Power Point (LMPP) and fail to reach the GMPP under Partial Shading Conditions (PSC). The main contribution of this work is the experimental validation of the DQN agent's implementation in a synchronous DC-DC Buck converter (step-down converter) un-der both uniform and PSC conditions. Additionally, we establish a testing pipeline for DRL models. The DQN agent's performance is evaluated alongside the P&O algorithm. Results consistently indicate the DQN agent's superiority over the P&O algorithm in all simulated scenarios. Although this trend does not entirely replicate in real-world test setups, significant results are observed. Specifically, in PSC sce-narios where the P&O algorithm becomes trapped at an LMPP, the DQN algorithm extracts up to 63.5 % more power than the P&O algorithm. An open repository is available, containing PCB schematic designs and layouts, along with the code used for model training and deployment.

Norm Augmented Reinforcement Learning Agents With Synthesized Normative Rules

The dynamic deontic (DD) is a norm synthesis framework that extracts normative rules from reinforcement learning (RL), however it was not designed to be applied in agent coordination. This study proposes a norm augmented reinforcement learning framework (NARLF) that extends said model to include a norm deliberation mechanism for learned norms re-imputation for norm biased decision-making RL agents. This study aims to test the effects of synthesized norms applied on-line and off-line on agent learning performance. The framework consists of the DD framework extended with a pre-processing and deliberation component to allow re-imputation of normative rules. A deliberation model, the Norm Augmented Q-Table (NAugQT), is proposed to map normative rules into RL agents via q-values weight updates. Results show that the framework is able to map and improve RL agent's performance but only when synthesized off-line edited absolute norm salience value norms are used. This shows limitations when unstable salience norms are applied. Improvement in norm extraction and pre-processing are required.

Human employees and service robots in the service encounter and the role of attribution of theory of mind

A frequently made assumption – supported in a large number of empirical studies – is that customer satisfaction stemming from a service encounter influences the customer's subsequent word-of-mouth activities. The present study re-examines this association with respect to both human service employees and service robots (which are expected to become more common in service encounters in the near future). First, it is assumed that the customer's attribution of theory of mind to a service agent is an important source of information for the formation of a satisfaction assessment. Indeed, it is assumed that the agent's theory of mind is a prerequisite for understanding the customer's needs. Second, in contrast to many existing studies, word-of-mouth is captured in terms of the valence of what customers actually say (as opposed to various forms of intentions to engage in word-of-mouth, which represent a dominant contemporary operationalization of word-of-mouth). A between-subjects experiment was conducted in which a service agent's identity (service robot vs. human) and service performance (poor vs. good) were the manipulated factors. The results show that both these factors influenced attribution of theory of mind to the agent, and that attribution of theory of mind enhanced customer satisfaction. The results also show that customer satisfaction affected word-of-mouth content in a valence-congruent way.

Partially Observable Hierarchical Reinforcement Learning with AI Planning (Student Abstract)

Partially observable Markov decision processes (POMDPs) challenge reinforcement learning agents due to incomplete knowledge of the environment. Even assuming monotonicity in uncertainty, it is difficult for an agent to know how and when to stop exploring for a given task. In this abstract, we discuss how to use hierarchical reinforcement learning (HRL) and AI Planning (AIP) to improve exploration when the agent knows possible valuations of unknown predicates and how to discover them. By encoding the uncertainty in an abstract planning model, the agent can derive a high-level plan which is then used to decompose the overall POMDP into a tree of semi-POMDPs for training. We evaluate our agent's performance on the MiniGrid domain and show how guided exploration may improve agent performance.

Boosting Communication Efficiency in Federated Learning for Multiagent-Based Multimicrogrid Energy Management.

Privacy of user is becoming increasingly significant in constructing efficient multiagent energy management systems for multimicrogrid (MMG). As an emerging privacy-protection method, federated learning (FL) has been used to prevent data breaches in the MMG-related field. However, with the ever-growing participants, the underlying communication burden existing in FL is evident. Besides, since the neural network layers collectively determine an agent's performance, the possible difference in layer convergence speeds would cause the inconsistency problem, that is, the FL may degrade the convergence rate of those fast-convergent layers, which weakens the overall performance of the agent. To address these issues, a communication-efficient FL (CEFL) algorithm is proposed in this study. Considering the cooperative relationship among layers, a layer evaluation (LE) mechanism is developed in CEFL to evaluate layer contribution through the Shapley value (SV), a profit distribution approach for coalitions. In this way, only partial layers with the highest contributions are selected to be uploaded to the server. In addition, instead of average parameters aggregation, a communication-efficient parameter aggregation method is proposed in CEFL to update the parameters of the global model (GM), in which an aggregation model (AM) is developed to receive parameters for aggregation. The performance of the proposed CEFL is verified by the numerical analysis of MMGs with 3-8 MGs participating. Furthermore, experiments investigate the influence of the hyperparameter in the CEFL and also demonstrate performance improvements, compared with the other four state-of-the-art algorithms.

Analaisis Pengaruh Insentif Dan Motivasi Terhadap Kinerja Dan Loyalitas Agen Perisai BPJSTK (Cabang Utama Surabaya)

BPJS Employment launched an agency system, the National Social Security Drive or named Perisai. Through the Perisai agency system, BPJS Employment seeks to expand the scope of membership. There was a policy change in February 2022 so research was carried out to analyze the influence of incentive and motivation programs on the performance and loyalty of shield agents. The analysis in this research carried out questionnaires distributed to 40 shield agents and processed using the Partial Least Square method using Smart PLS. This research showed that the incentive program influenced performance, while motivation variables did not influence performance, and performance influenced the loyalty of the shield agent's performance.

Development, implementation, and impact analysis of model predictive control-based optimal precooling using smart home thermostats

Model Predictive Control (MPC)-based precooling strategies are typically analyzed through simulations. Their field studies in residential buildings are quite limited due to hardware retrofitting costs, lengthy parameter identification periods, and the need to have homeowners' participation. Therefore, there is a lack of MPC-based precooling impact analysis using field data which may have prevented widespread adoption of the technology. To address this issue, in this paper we developed an MPC agent and implemented it on an online cloud-based platform. The MPC agent makes use of a gray-box model to capture the home thermal dynamics, a novel set of constraints to ensure that the model parameters identified are realistic, and a node sensor to provide interior wall surface temperature measurement. To evaluate its performance and conduct impact analysis, we introduced a modified matrix profile-based weather clustering algorithm and two performance indicators for cost saving and energy flexibility. We also carried out extensive field tests on nine homes over a period of four months. Our results show that the MPC agent can reduce energy cost by 28.72%–51.31% on hot summer days and by up to 60.32% on mild summer days, in addition to achieving significant energy flexibility. Moreover, the agent's performance is found to be most impacted by weather conditions, AC performance, user comfort preferences, and floor areas of the homes.

Examining ChatGPT Performance on USMLE Sample Items and Implications for Assessment.

In late 2022 and early 2023, reports that ChatGPT could pass the United States Medical Licensing Examination (USMLE) generated considerable excitement, and media response suggested ChatGPT has credible medical knowledge. This report analyzes the extent to which an artificial intelligence (AI) agent's performance on these sample items can generalize to performance on an actual USMLE examination and an illustration is given using ChatGPT. As with earlier investigations, analyses were based on publicly available USMLE sample items. Each item was submitted to ChatGPT (version 3.5) 3 times to evaluate stability. Responses were scored following rules that match operational practice, and a preliminary analysis explored the characteristics of items that ChatGPT answered correctly. The study was conducted between February and March 2023. For the full sample of items, ChatGPT scored above 60% correct except for one replication for Step 3. Response success varied across replications for 76 items (20%). There was a modest correspondence with item difficulty wherein ChatGPT was more likely to respond correctly to items found easier by examinees. ChatGPT performed significantly worse ( P < .001) on items relating to practice-based learning. Achieving 60% accuracy is an approximate indicator of meeting the passing standard, requiring statistical adjustments for comparison. Hence, this assessment can only suggest consistency with the passing standards for Steps 1 and 2 Clinical Knowledge, with further limitations in extrapolating this inference to Step 3. These limitations are due to variances in item difficulty and exclusion of the simulation component of Step 3 from the evaluation-limitations that would apply to any AI system evaluated on the Step 3 sample items. It is crucial to note that responses from large language models exhibit notable variations when faced with repeated inquiries, underscoring the need for expert validation to ensure their utility as a learning tool.

Aspects of Life Insurance Agents' Performance in Vietnam: A Study from the Impact of Customer-Oriented Behavior

This study examined the influence of life insurance agents' customer-oriented action research on aspects of agents' personal sales performance. In particular, the agent's performance is considered in terms of behavioral effectiveness and outcome performance. The research was conducted through interviews and surveys of insurance agents of life insurance businesses in Hanoi city, with 158 feedback forms received. Data collection is group processed through supporting software support SPSS and PLS-SEM. The study results show that customer-oriented behavior substantially impacts life insurance agents' behavioral performance more than outcome performance. At the same time, behavioral performance also plays a mediating role in providing the performance of customer-oriented behavior to the performance outcomes of life insurance agents. The research results are the basis for the authors to propose some key tips for life insurance businesses in the current context of Vietnam's insurance market.

Mastering air combat game with deep reinforcement learning

Reinforcement learning has been applied to air combat problems in recent years, and the idea of curriculum learning is often used for reinforcement learning, but traditional curriculum learning suffers from the problem of plasticity loss in neural networks. Plasticity loss is the difficulty of learning new knowledge after the network has converged. To this end, we propose a motivational curriculum learning distributed proximal policy optimization (MCLDPPO) algorithm, through which trained agents can significantly outperform the predictive game tree and mainstream reinforcement learning methods. The motivational curriculum learning is designed to help the agent gradually improve its combat ability by observing the agent’s unsatisfactory performance and providing appropriate rewards as a guide. Furthermore, a complete tactical maneuver is encapsulated based on the existing air combat knowledge, and through the flexible use of these maneuvers, some tactics beyond human knowledge can be realized. In addition, we designed an interruption mechanism for the agent to increase the frequency of decision-making when the agent faces an emergency. When the number of threats received by the agent changes, the current action is interrupted in order to reacquire observations and make decisions again. Using the interruption mechanism can significantly improve the performance of the agent. To simulate actual air combat better, we use digital twin technology to simulate real air battles and propose a parallel battlefield mechanism that can run multiple simulation environments simultaneously, effectively improving data throughput. The experimental results demonstrate that the agent can fully utilize the situational information to make reasonable decisions and provide tactical adaptation in the air combat, verifying the effectiveness of the algorithmic framework proposed in this paper.

Optimal Reactive Power Dispatch in ADNs using DRL and the Impact of Its Various Settings and Environmental Changes.

Modern active distribution networks (ADNs) witness increasing complexities that require efforts in control practices, including optimal reactive power dispatch (ORPD). Deep reinforcement learning (DRL) is proposed to manage the network's reactive power by coordinating different resources, including distributed energy resources, to enhance performance. However, there is a lack of studies examining DRL elements' performance sensitivity. To this end, in this paper we examine the impact of various DRL reward representations and hyperparameters on the agent's learning performance when solving the ORPD problem for ADNs. We assess the agent's performance regarding accuracy and training time metrics, as well as critic estimate measures. Furthermore, different environmental changes are examined to study the DRL model's scalability by including other resources. Results show that compared to other representations, the complementary reward function exhibits improved performance in terms of power loss minimization and convergence time by 10-15% and 14-18%, respectively. Also, adequate agent performance is observed to be neighboring the best-suited value of each hyperparameter for the studied problem. In addition, scalability analysis depicts that increasing the number of possible action combinations in the action space by approximately nine times results in 1.7 times increase in the training time.

Multi-Horizon Learning in Procedurally-Generated Environments for Off-Policy Reinforcement Learning (Student Abstract)

Value estimates at multiple timescales can help create advanced discounting functions and allow agents to form more effective predictive models of their environment. In this work, we investigate learning over multiple horizons concurrently for off-policy reinforcement learning by using an advantage-based action selection method and introducing architectural improvements. Our proposed agent learns over multiple horizons simultaneously, while using either exponential or hyperbolic discounting functions. We implement our approach on Rainbow, a value-based off-policy algorithm, and test on Procgen, a collection of procedurally-generated environments, to demonstrate the effectiveness of this approach, specifically to evaluate the agent's performance in previously unseen scenarios.

Reinforcement-learning-based actuator selection method for active flow control

This paper addresses the issue of actuator selection for active flow control by proposing a novel method built on top of a reinforcement learning agent. Starting from a pre-trained agent using numerous actuators, the algorithm estimates the impact of a potential actuator removal on the value function, indicating the agent's performance. It is applied to two test cases, the one-dimensional Kuramoto–Sivashinsky equation and a laminar bidimensional flow around an airfoil at$Re=1000$for different angles of attack ranging from$12^{\circ }$to$20^{\circ }$, to demonstrate its capabilities and limits. The proposed actuator-sparsification method relies on a sequential elimination of the least relevant action components, starting from a fully developed layout. The relevancy of each component is evaluated using metrics based on the value function. Results show that, while still being limited by this intrinsic elimination paradigm (i.e. the sequential elimination), actuator patterns and obtained policies demonstrate relevant performances and allow us to draw an accurate approximation of the Pareto front of performances versus actuator budget.

Artificial Intelligence Enables Real-Time and Intuitive Control of Prostheses via Nerve Interface.

The next generation prosthetic hand that moves and feels like a real hand requires a robust neural interconnection between the human minds and machines. Here we present a neuroprosthetic system to demonstrate that principle by employing an artificial intelligence (AI) agent to translate the amputee's movement intent through a peripheral nerve interface. The AI agent is designed based on the recurrent neural network (RNN) and could simultaneously decode six degree-of-freedom (DOF) from multichannel nerve data in real-time. The decoder's performance is characterized in motor decoding experiments with three human amputees. First, we show the AI agent enables amputees to intuitively control a prosthetic hand with individual finger and wrist movements up to 97-98% accuracy. Second, we demonstrate the AI agent's real-time performance by measuring the reaction time and information throughput in a hand gesture matching task. Third, we investigate the AI agent's long-term uses and show the decoder's robust predictive performance over a 16-month implant duration. Conclusion & significance: Our study demonstrates the potential of AI-enabled nerve technology, underling the next generation of dexterous and intuitive prosthetic hands.

Curiosity-Driven Exploration via Latent Bayesian Surprise

The human intrinsic desire to pursue knowledge, also known as curiosity, is considered essential in the process of skill acquisition. With the aid of artificial curiosity, we could equip current techniques for control, such as Reinforcement Learning, with more natural exploration capabilities. A promising approach in this respect has consisted of using Bayesian surprise on model parameters, i.e. a metric for the difference between prior and posterior beliefs, to favour exploration. In this contribution, we propose to apply Bayesian surprise in a latent space representing the agent’s current understanding of the dynamics of the system, drastically reducing the computational costs. We extensively evaluate our method by measuring the agent's performance in terms of environment exploration, for continuous tasks, and looking at the game scores achieved, for video games. Our model is computationally cheap and compares positively with current state-of-the-art methods on several problems. We also investigate the effects caused by stochasticity in the environment, which is often a failure case for curiosity-driven agents. In this regime, the results suggest that our approach is resilient to stochastic transitions.

Effectiveness of a competence‐based planting support training programme for development agents in Ethiopia

AbstractCompetence‐based education and training (CBE/T) has been implemented in Ethiopia to develop the competences of (future) professionals and to improve their performance. However, empirical evidence that demonstrates the effectiveness of CBE/T is scarce. Positioning the study within the theory of strategic alignment and comprehensive competence‐based training, we used the authentic core job task ‘On‐Site Helping of Farmers during the Planting of Maize’, of Development Agents as problem context and conducted an experimental‐longitudinal research study including multirater performance assessment. The study compared competence development of the Development Agents who received training that could be characterized as ‘High‐CBT’ (N = 33) and ‘Low‐CBT’ (N = 32). ‘High‐CBT’ means that in these training programmes, principles of competence‐based training were used more completely than in the ‘Low‐CBT’ programmes. Experts rated the competence levels of the Development Agents and Development Agents rated their own competence levels. Both groups did that before and after the training. Individual Development Agent performance was also rated by Trained Assessors. Longitudinally, Development Agent performance data was collected during one production year at three points in time. Development Agent's competence development in the ‘High‐CBT’ training condition was higher than in the ‘Low‐CBT’ condition. Observations made on each Development Agent's performance by Trained Assessors both in the Farmer Training Centres and in the authentic job situations, generally confirmed better performance of the ‘High‐CBT’ group compared with the ‘Low‐CBT’ group. The finding contributes to the state of research on the relationship between competence development and performance improvement, which is theoretically postulated although less empirically tested.

Exploration for Countering the Episodic Memory.

Reinforcement learning is a prominent computational approach for goal-directed learning and decision making, and exploration plays an important role in improving the agent's performance in reinforcement learning. In low-dimensional Markov decision processes, table reinforcement learning incorporated within count-based exploration works well for states of the Markov decision processes that can be easily exhausted. It is generally accepted that count-based exploration strategies turn inefficient when applied to high-dimensional Markov decision processes (generally high-dimensional state spaces, continuous action spaces, or both) since most states occur only once in deep reinforcement learning. Exploration methods widely applied in deep reinforcement learning rely on heuristic intrinsic motivation to explore unseen states or unreached parts of one state. The episodic memory module simulates the performance of hippocampus in human brain. This is exactly the memory of past experience. It seems logical to use episodic memory to count the situations encountered. Therefore, we use the contextual memory module to remember the states that the agent has encountered, as a count of states, and the purpose of exploration is to reduce the probability of encountering these states again. The purpose of exploration is to counter the episodic memory. In this article, we try to take advantage of the episodic memory module to estimate the number of states experienced, so as to counter the episodic memory. We conducted experiments on the OpenAI platform and found that counting accuracy of state is higher than that of the CTS model. At the same time, this method is used in high-dimensional object detection and tracking, also achieving good results.

The role of emotional intelligence on the performance of real estate agents in Prishtina, Kosovo

PurposeThe purpose of this study was to explore the effect of emotional intelligence (EI) on the performance of real estate agents in Prishtina, Kosovo. The study also investigated the relationship of each dimension of emotional intelligence with the real estate agent's performance (REAP) in Prishtina, which is the city with the largest number of real estate agents in Kosovo.Design/methodology/approachThe present study used quantitative research with the questionnaire used as a research instrument. The questionnaire survey was conducted with 78 real estate agents in Prishtina, Kosovo. The sampling method used in this research was random sampling.FindingsThe findings of this study indicated that emotional intelligence has a significant impact on the job performance of real estate agents. The study also found that relationship management (RM) and social awareness (SOA) have a strong effect on real estate agents' performance, whereas self-awareness (SA) does not seem to have any statistically significant explanatory power over REAP.Research limitations/implicationsThis study can be utilized as a landmark for agents of real estate on understanding how the agents can use emotional intelligence in agents' favor by pointing out the prominence of EI in realizing the needs and desires of the potential buyers and the influence EI has on the decision to buy property. Furthermore, through this study, the real estate agencies will be provided with multiple reasons that substantiate the necessity to hire emotionally trained agents, and besides professional preparation, the companies must provide employees with behavioral training.Originality/valueThe present study is the first quantification of the impact of emotional intelligence and dimensions of emotional intelligence on the performance of Prishtina's real estate agents.

A Model-Free Approach to Intrusion Response Systems

With the rising number of data breaches, denial of service attacks and general malicious activity facing modern computer networks, there is an increasing need to quickly and effectively respond to attacks. Intrusion Detection Systems provide an automated method of identifying malicious activity within a network however the development of an Intrusion Response System which can automatically respond to these alerts is non-trivial. Current research in IRS proposes model-based methods for identifying possible routes a malicious actor may take when attacking a network and use subjective performance values for the cost and benefit of a response, both of which can be invalidated by the increasingly dynamic nature of network topologies and system configurations. The IRS proposed in this work utilises a Model-free Reinforcement Learning approach and evaluates the Reinforcement Learning agent's performance in stopping two distinct multi-stage attack scenarios on a virtualised testbed. Experimentation demonstrates that the agent can successfully halt both attack scenarios and find responses which have minimal impact on normal network operation based on experience gained through training. A further contribution is the novel use of a virtualised environment that demonstrates Intrusion Response Reinforcement Learning performance in a more realistic environment than simulated tasks common to previous literature.