Efficient exploration strategy is one of essential issues in cooperative multi-agent reinforcement learning (MARL) algorithms requiring complex coordination. In this study, we introduce a new exploration method with the strangeness that can be easily incorporated into any centralized training and decentralized execution (CTDE)-based MARL algorithms. The strangeness refers to the degree of unfamiliarity of the observations that an agent visits. In order to give the observation strangeness a global perspective, it is also augmented with the the degree of unfamiliarity of the visited entire state. The exploration bonus is obtained from the strangeness and the proposed exploration method is not much affected by stochastic transitions commonly observed in MARL tasks. To prevent a high exploration bonus from making the MARL training insensitive to extrinsic rewards, we also propose a separate action-value function trained by both extrinsic reward and exploration bonus, on which a behavioral policy to generate transitions is designed based. It makes the CTDE-based MARL algorithms more stable when they are used with an exploration method. Through a comparative evaluation in didactic examples and the StarCraft Multi-Agent Challenge, we show that the proposed exploration method achieves significant performance improvement in the CTDE-based MARL algorithms.

In multi-agent systems with large number of agents, typically the contribution of each agent to the value of other agents is minimal (e.g., aggregation systems such as Uber, Deliveroo). In this paper, we consider such multi-agent systems where each agent is self-interested and takes a sequence of decisions and represent them as a Stochastic Non-atomic Congestion Game (SNCG). We derive key properties for equilibrium solutions in SNCG model with non-atomic and also nearly non-atomic agents. With those key equilibrium properties, we provide a novel Multi-Agent Reinforcement Learning (MARL) mechanism that minimizes variance across values of agents in the same state. To demonstrate the utility of this new mechanism, we provide detailed results on a real-world taxi dataset and also a generic simulator for aggregation systems. We show that our approach reduces the variance in revenues earned by taxi drivers, while still providing higher joint revenues than leading approaches.

Scientists and philosophers have debated whether humans can trust advanced artificial intelligence (AI) agents to respect humanity's best interests. Yet what about the reverse? Will advanced AI agents trust humans? Gauging an AI agent's trust in humans is challenging because--absent costs for dishonesty--such agents might respond falsely about their trust in humans. Here we present a method for incentivizing machine decisions without altering an AI agent's underlying algorithms or goal orientation. In two separate experiments, we then employ this method in hundreds of trust games between an AI agent (a Large Language Model (LLM) from OpenAI) and a human experimenter (author TJ). In our first experiment, we find that the AI agent decides to trust humans at higher rates when facing actual incentives than when making hypothetical decisions. Our second experiment replicates and extends these findings by automating game play and by homogenizing question wording. We again observe higher rates of trust when the AI agent faces real incentives. Across both experiments, the AI agent's trust decisions appear unrelated to the magnitude of stakes. Furthermore, to address the possibility that the AI agent's trust decisions reflect a preference for uncertainty, the experiments include two conditions that present the AI agent with a non-social decision task that provides the opportunity to choose a certain or uncertain option; in those conditions, the AI agent consistently chooses the certain option. Our experiments suggest that one of the most advanced AI language models to date alters its social behavior in response to incentives and displays behavior consistent with trust toward a human interlocutor when incentivized.

Figure 1: Within this work, we differentiate between various levels of image understanding: The original image (first row, left) can be interpreted as a panoramic semantic map (second row, left) by assigning a label to each pixel without differentiating between different instances of countable objects. Instances of countable objects are distinguished in the panoramic instance understanding (second row, right). The panoramic panoptic understanding (first row, right), which is the proposed method in this paper, builds on top of the previous understandings by eliminating their shortcomings: If possible different instances are distinguished and we guarantee that a label is assigned to each pixel. Abstract--In this work, we introduce panoramic panoptic combining supervised and contrastive training. A complete surrounding understanding provides a maximum of information to a mobile agent. ANOPTIC segmentation is the so far most complete segmentation task to describe the context of an image [1]. The domain shift from pinhole-to panoramic images is no exception. These properties have not been observed by the model during the training and make their correct segmentation Field of View challenging. Feature (PRF) framework which allows us to generate robust backbones via a contrastive pretext task. This poses severe problems due to the lack of does not only encourage similar features to be represented information containing the entire surrounding and the inability in a similar manner but more important, it pushes dissimilar of the agent to make proper decisions which may even lead features away from each other [16], [17]. This leads to well to accidents [5]. Thus, both pieces of information are equally separated clusters in the latent space of the backbone which important: the image should cover the entire surrounding and proves to mitigate distribution shift performance drops.

We investigate a data quality-aware dynamic client selection problem for multiple federated learning (FL) services in a wireless network, where each client offers dynamic datasets for the simultaneous training of multiple FL services, and each FL service demander has to pay for the clients under constrained monetary budgets. The problem is formalized as a non-cooperative Markov game over the training rounds. A multi-agent hybrid deep reinforcement learning-based algorithm is proposed to optimize the joint client selection and payment actions, while avoiding action conflicts. Simulation results indicate that our proposed algorithm can significantly improve training performance.

This study proposes an approach for establishing an optimal multihop ad-hoc network using multiple unmanned aerial vehicles (UAVs) to provide emergency communication in disaster areas. The approach includes two stages, one uses particle swarm optimization (PSO) to find optimal positions to deploy UAVs, and the other uses a behavior-based controller to navigate the UAVs to their assigned positions without colliding with obstacles in an unknown environment. Several constraints related to the UAVs' sensing and communication ranges have been imposed to ensure the applicability of the proposed approach in real-world scenarios. A number of simulation experiments with data loaded from real environments have been conducted. The results show that our proposed approach is not only successful in establishing multihop ad-hoc routes but also meets the requirements for real-time deployment of UAVs.

In recent years, the exponential proliferation of smart devices with their intelligent applications poses severe challenges on conventional cellular networks. Such challenges can be potentially overcome by integrating communication, computing, caching, and control (i4C) technologies. In this survey, we first give a snapshot of different aspects of the i4C, comprising background, motivation, leading technological enablers, potential applications, and use cases. Next, we describe different models of communication, computing, caching, and control (4C) to lay the foundation of the integration approach. We review current state-of-the-art research efforts related to the i4C, focusing on recent trends of both conventional and artificial intelligence (AI)-based integration approaches. We also highlight the need for intelligence in resources integration. Then, we discuss integration of sensing and communication (ISAC) and classify the integration approaches into various classes. Finally, we propose open challenges and present future research directions for beyond 5G networks, such as 6G.

Interaction and cooperation with humans are overarching aspirations of artificial intelligence (AI) research. Recent studies demonstrate that AI agents trained with deep reinforcement learning are capable of collaborating with humans. These studies primarily evaluate human compatibility through "objective" metrics such as task performance, obscuring potential variation in the levels of trust and subjective preference that different agents garner. To better understand the factors shaping subjective preferences in human-agent cooperation, we train deep reinforcement learning agents in Coins, a two-player social dilemma. We recruit participants for a human-agent cooperation study and measure their impressions of the agents they encounter. Participants' perceptions of warmth and competence predict their stated preferences for different agents, above and beyond objective performance metrics. Drawing inspiration from social science and biology research, we subsequently implement a new "partner choice" framework to elicit revealed preferences: after playing an episode with an agent, participants are asked whether they would like to play the next round with the same agent or to play alone. As with stated preferences, social perception better predicts participants' revealed preferences than does objective performance. Given these results, we recommend human-agent interaction researchers routinely incorporate the measurement of social perception and subjective preferences into their studies.

Hierarchical Reinforcement Learning (HRL) algorithms have been demonstrated to perform well on high-dimensional decision making and robotic control tasks. However, because they solely optimize for rewards, the agent tends to search the same space redundantly. This problem reduces the speed of learning and achieved reward. In this work, we present an Off-Policy HRL algorithm that maximizes entropy for efficient exploration. The algorithm learns a temporally abstracted low-level policy and is able to explore broadly through the addition of entropy to the high-level. The novelty of this work is the theoretical motivation of adding entropy to the RL objective in the HRL setting. We empirically show that the entropy can be added to both levels if the Kullback-Leibler (KL) divergence between consecutive updates of the low-level policy is sufficiently small. We performed an ablative study to analyze the effects of entropy on hierarchy, in which adding entropy to high-level emerged as the most desirable configuration. Furthermore, a higher temperature in the low-level leads to Q-value overestimation and increases the stochasticity of the environment that the high-level operates on, making learning more challenging. Our method, SHIRO, surpasses state-of-the-art performance on a range of simulated robotic control benchmark tasks and requires minimal tuning.

In this research, we are about to present an agentbased model of human muscle which can be used in analysis of human movement. As the model is designed based on the physiological structure of the muscle, The simulation calculations would be natural, and also, It can be possible to analyze human movement using reverse engineering methods. The model is also a suitable choice to be used in modern prostheses, because the calculation of the model is less than other machine learning models such as artificial neural network algorithms and It makes our algorithm battery-friendly. We will also devise a method that can calculate the intensity of human muscle during gait cycle using a reverse engineering solution. The algorithm called Boots is different from some optimization methods, so It would be able to compute the activities of both agonist and antagonist muscles in a joint. As a consequence, By having an agent-based model of human muscle and Boots algorithm, We would be capable to develop software that can calculate the nervous stimulation of human's lower body muscle based on the angular displacement during gait cycle without using painful methods like electromyography. By developing the application as open-source software, We are hopeful to help researchers and physicians who are studying in medical and biomechanical fields.