Spiking neural networks (SNNs) are widely applied in various fields due to their energy-efficient and fast-inference capabilities. Applying SNNs to reinforcement learning (RL) can significantly reduce the computational resource requirements for agents and improve the algorithm's performance under resource-constrained conditions. However, in current spiking reinforcement learning (SRL) algorithms, the simulation results of multiple time steps can only correspond to a single-step decision in RL. This is quite different from the real temporal dynamics in the brain and also fails to fully exploit the capacity of SNNs to process temporal data. In order to address this temporal mismatch issue and further take advantage of the inherent temporal dynamics of spiking neurons, we propose a novel temporal alignment paradigm (T AP) that leverages the single-step update of spiking neurons to accumulate historical state information in RL and introduces gated units to enhance the memory capacity of spiking neurons. Experimental results show that our method can solve partially observable Markov decision processes (POMDPs) and multi-agent cooperation problems with similar performance as recurrent neural networks (RNNs) but with about 50% power consumption.

Subjective Logic (SL) is a logic incorporating uncertainty and opinions for agents in dynamic systems. In this work, we investigate the use of subjective logic to model opinions and belief change in social networks. In particular, we work toward the development of a subjective logic belief/opinion update function appropriate for modeling belief change as communication occurs in social networks. We found through experiments that an update function with belief fusion from SL does not have ideal properties to represent a rational update. Even without these properties, we found that an update function with cumulative belief fusion can describe behaviors not explored by the social network model defined by Alvim, Knight, and Valencia (2019).

This paper presents BattleAgent, an emulation system that combines the Large Vision-Language Model and Multi-agent System. This novel system aims to simulate complex dynamic interactions among multiple agents, as well as between agents and their environments, over a period of time. It emulates both the decision-making processes of leaders and the viewpoints of ordinary participants, such as soldiers. The emulation showcases the current capabilities of agents, featuring fine-grained multi-modal interactions between agents and landscapes. It develops customizable agent structures to meet specific situational requirements, for example, a variety of battle-related activities like scouting and trench digging. These components collaborate to recreate historical events in a lively and comprehensive manner while offering insights into the thoughts and feelings of individuals from diverse viewpoints. The technological foundations of BattleAgent establish detailed and immersive settings for historical battles, enabling individual agents to partake in, observe, and dynamically respond to evolving battle scenarios. This methodology holds the potential to substantially deepen our understanding of historical events, particularly through individual accounts. Such initiatives can also aid historical research, as conventional historical narratives often lack documentation and prioritize the perspectives of decision-makers, thereby overlooking the experiences of ordinary individuals. BattelAgent illustrates AI's potential to revitalize the human aspect in crucial social events, thereby fostering a more nuanced collective understanding and driving the progressive development of human society.

Elon Musk has claimed'AI will be smarter than any human by the end of 2025' - and while that is just one year away, an expert said the prediction may still come true. Nell Watson, an AI expert and ethicist, has shared a detailed timeline of how the tech could transform from chatbots to super intelligent agents over the next 12 months. The path would start with a massive 100 billion investment in new computing infrastructure, then AI would learn how to self-improve until it becomes'conscious.' 'Although one year is a short time frame, remember that only 15 months have passed since ChatGPT's breakthrough, which thrust AI into the public consciousness, she told DailyMail.com. 'Developments continue at a frenetic pace since, and even appear to be rapidly accelerating.' Elon Musk has claimed'AI will be smarter than any human by the end of 2025' - and while that is just one year away, an expert said the prediction may still come true Watson, who is the author of'Taming the Machine: Ethically harness the power of AI,' described superhuman AI as systems that far exceed human capabilities across the board.

With the rapid development of underwater communication, sensing, automation, robot technologies, autonomous underwater vehicle (AUV) swarms are gradually becoming popular and have been widely promoted in ocean exploration and underwater tracking or surveillance, etc. However, the complex underwater environment poses significant challenges for AUV swarm-based accurate tracking for the underwater moving targets. In this paper, we aim at proposing a multi-AUV cooperative underwater multi-target tracking algorithm especially when the real underwater factors are taken into account.We first give normally modelling approach for the underwater sonar-based detection and the ocean current interference on the target tracking process.Then, we regard the AUV swarm as a underwater ad-hoc network and propose a novel Multi-Agent Reinforcement Learning (MARL) architecture towards the AUV swarm based on Software-Defined Networking (SDN).It enhances the flexibility and scalability of the AUV swarm through centralized management and distributed operations.Based on the proposed MARL architecture, we propose the "dynamic-attention switching" and "dynamic-resampling switching" mechanisms, to enhance the efficiency and accuracy of AUV swarm cooperation during task execution.Finally, based on a proposed AUV classification method, we propose an efficient cooperative tracking algorithm called ASMA.Evaluation results demonstrate that our proposed tracking algorithm can perform precise underwater multi-target tracking, comparing with many of recent research products in terms of convergence speed and tracking accuracy.

Automatic depression detection from conversational data has gained significant interest in recent years. The DAIC-WOZ dataset, interviews conducted by a human-controlled virtual agent, has been widely used for this task. Recent studies have reported enhanced performance when incorporating interviewer's prompts into the model. In this work, we hypothesize that this improvement might be mainly due to a bias present in these prompts, rather than the proposed architectures and methods. Through ablation experiments and qualitative analysis, we discover that models using interviewer's prompts learn to focus on a specific region of the interviews, where questions about past experiences with mental health issues are asked, and use them as discriminative shortcuts to detect depressed participants. In contrast, models using participant responses gather evidence from across the entire interview. Finally, to highlight the magnitude of this bias, we achieve a 0.90 F1 score by intentionally exploiting it, the highest result reported to date on this dataset using only textual information. Our findings underline the need for caution when incorporating interviewers' prompts into models, as they may inadvertently learn to exploit targeted prompts, rather than learning to characterize the language and behavior that are genuinely indicative of the patient's mental health condition.

Opportunistic spectrum access has the potential to increase the efficiency of spectrum utilization in cognitive radio networks (CRNs). In CRNs, both spectrum sensing and resource allocation (SSRA) are critical to maximizing system throughput while minimizing collisions of secondary users with the primary network. However, many works in dynamic spectrum access do not consider the impact of imperfect sensing information such as mis-detected channels, which the additional information available in joint SSRA can help remediate. In this work, we examine joint SSRA as an optimization which seeks to maximize a CRN's net communication rate subject to constraints on channel sensing, channel access, and transmit power. Given the non-trivial nature of the problem, we leverage multi-agent reinforcement learning to enable a network of secondary users to dynamically access unoccupied spectrum via only local test statistics, formulated under the energy detection paradigm of spectrum sensing. In doing so, we develop a novel multi-agent implementation of hybrid soft actor critic, MHSAC, based on the QMIX mixing scheme. Through experiments, we find that our SSRA algorithm, HySSRA, is successful in maximizing the CRN's utilization of spectrum resources while also limiting its interference with the primary network, and outperforms the current state-of-the-art by a wide margin. We also explore the impact of wireless variations such as coherence time on the efficacy of the system.

This article introduces Follow-Me AI, a concept designed to enhance user interactions with smart environments, optimize energy use, and provide better control over data captured by these environments. Through AI agents that accompany users, Follow-Me AI negotiates data management based on user consent, aligns environmental controls as well as user communication and computes resources available in the environment with user preferences, and predicts user behavior to proactively adjust the smart environment. The manuscript illustrates this concept with a detailed example of Follow-Me AI in a smart campus setting, detailing the interactions with the building's management system for optimal comfort and efficiency. Finally, this article looks into the challenges and opportunities related to Follow-Me AI.

In this paper, we propose the Liquid-Graph Time-constant (LGTC) network, a continuous graph neural network(GNN) model for control of multi-agent systems based on therecent Liquid Time Constant (LTC) network. We analyse itsstability leveraging contraction analysis and propose a closed-form model that preserves the model contraction rate and doesnot require solving an ODE at each iteration. Compared todiscrete models like Graph Gated Neural Networks (GGNNs),the higher expressivity of the proposed model guaranteesremarkable performance while reducing the large amountof communicated variables normally required by GNNs. Weevaluate our model on a distributed multi-agent control casestudy (flocking) taking into account variable communicationrange and scalability under non-instantaneous communication

We describe an approach for aligning an LLM-based dialogue agent based on global (i.e., dialogue-level) rewards, while also taking into account naturally-occurring multimodal signals. At a high level, our approach (dubbed GELI) learns a local, turn-level reward model by decomposing the human-provided Global Explicit (GE) session-level reward, using Local Implicit (LI) multimodal reward signals to crossmodally shape the reward decomposition step. This decomposed reward model is then used as part of the standard RHLF pipeline improve an LLM-based dialog agent. We run quantitative and qualitative human studies to evaluate the performance of our GELI approach, and find that it shows consistent improvements across various conversational metrics compared to baseline methods.