This paper develops a natural-language agent-based model of argumentation (ABMA). Its artificial deliberative agents (ADAs) are constructed with the help of so-called neural language models recently developed in AI and computational linguistics. ADAs are equipped with a minimalist belief system and may generate and submit novel contributions to a conversation. The natural-language ABMA allows us to simulate collective deliberation in English, i.e. with arguments, reasons, and claims themselves -- rather than with their mathematical representations (as in formal models). This paper uses the natural-language ABMA to test the robustness of formal reason-balancing models of argumentation [Maes & Flache 2013, Singer et al. 2019]: First of all, as long as ADAs remain passive, confirmation bias and homophily updating trigger polarization, which is consistent with results from formal models. However, once ADAs start to actively generate new contributions, the evolution of a conservation is dominated by properties of the agents *as authors*. This suggests that the creation of new arguments, reasons, and claims critically affects a conversation and is of pivotal importance for understanding the dynamics of collective deliberation. The paper closes by pointing out further fruitful applications of the model and challenges for future research.

This paper presents a new algorithm named spherical vector-based particle swarm optimization (SPSO) to deal with the problem of path planning for unmanned aerial vehicles (UAVs) in complicated environments subjected to multiple threats. A cost function is first formulated to convert the path planning into an optimization problem that incorporates requirements and constraints for the feasible and safe operation of the UAV. SPSO is then used to find the optimal path that minimizes the cost function by efficiently searching the configuration space of the UAV via the correspondence between the particle position and the speed, turn angle and climb/dive angle of the UAV. To evaluate the performance of SPSO, eight benchmarking scenarios have been generated from real digital elevation model maps. The results show that the proposed SPSO outperforms not only other particle swarm optimization (PSO) variants including the classic PSO, phase angle-encoded PSO and quantum-behave PSO but also other state-of-the-art metaheuristic optimization algorithms including the genetic algorithm (GA), artificial bee colony (ABC), and differential evolution (DE) in most scenarios. In addition, experiments have been conducted to demonstrate the validity of the generated paths for real UAV operations. Source code of the algorithm can be found at https://github.com/duongpm/SPSO.

A key step in influence maximization in online social networks is the identification of a small number of users, known as influencers, who are able to spread influence quickly and widely to other users. The evolving nature of the topological structure of these networks makes it difficult to locate and identify these influencers. In this paper, we propose an adaptive agent-based evolutionary approach to address this problem in the context of both static and dynamic networks. This approach is shown to be able to adapt the solution as the network evolves. It is also applicable to large-scale networks due to its distributed framework. Evaluation of our approach is performed by using both synthetic networks and real-world datasets. Experimental results demonstrate that the proposed approach outperforms state-of-the-art seeding algorithms in terms of maximizing influence.

Since the number of elderly and patients who are in hospitals and healthcare centers are growing, providing efficient remote healthcare services seems very important. Currently, most such systems benefit from the distribution and autonomy features of multiagent systems and the structure of wireless sensor networks. On the one hand, securing the data of remote healthcare systems is one of the most significant concerns; particularly recent types of research about the security of remote healthcare systems keep them secure from eavesdropping and data modification. On the other hand, existing remote healthcare systems are still vulnerable against other common attacks of healthcare networks such as Denial of Service (DoS) and User to Root (U2R) attacks, because they are managed remotely and based on the Internet. Therefore, in this paper, we propose a secure framework for remote healthcare systems that consists of two phases. First, we design a healthcare system base on multiagent technology to collect data from a sensor network. Then, in the second phase, a layered architecture of intrusion detection systems that uses Support Vector Machine to learn the behavior of network traffic is applied. Based on our framework, we implement a secure remote healthcare system and evaluate this system against the frequent attacks of healthcare networks such as Smurf, Buffer overflow, Neptune, and Pod attacks. In the end, evaluation parameters of the layered architecture of intrusion detection systems prove the efficiency and correctness of our proposed framework.

The automation of functional testing in software has allowed developers to continuously check for negative impacts on functionality throughout the iterative phases of development. This is not the case for User eXperience (UX), which has hitherto relied almost exclusively on testing with real users. User testing is a slow endeavour that can become a bottleneck for development of interactive systems. To address this problem, we here propose an agent based approach for automatic UX testing. We develop agents with basic problem solving skills and a core affect model, allowing us to model an artificial affective state as they traverse different levels of a game. Although this research is still at a primordial state, we believe the results here presented make a strong case for the use of intelligent agents endowed with affective computing models for automating UX testing.

We propose a novel policy update that combines regularized policy optimization with model learning as an auxiliary loss. The update (henceforth Muesli) matches MuZero's state-of-the-art performance on Atari. Notably, Muesli does so without using deep search: it acts directly with a policy network and has computation speed comparable to model-free baselines. The Atari results are complemented by extensive ablations, and by additional results on continuous control and 9x9 Go.

In multi-agent reinforcement learning, the cooperative learning behavior of agents is very important. In the field of heterogeneous multi-agent reinforcement learning, cooperative behavior among different types of agents in a group is pursued. Learning a joint-action set during centralized training is an attractive way to obtain such cooperative behavior, however, this method brings limited learning performance with heterogeneous agents. To improve the learning performance of heterogeneous agents during centralized training, two-stage heterogeneous centralized training which allows the training of multiple roles of heterogeneous agents is proposed. During training, two training processes are conducted in a series. One of the two stages is to attempt training each agent according to its role, aiming at the maximization of individual role rewards. The other is for training the agents as a whole to make them learn cooperative behaviors while attempting to maximize shared collective rewards, e.g., team rewards. Because these two training processes are conducted in a series in every timestep, agents can learn how to maximize role rewards and team rewards simultaneously. The proposed method is applied to 5 versus 5 AI robot soccer for validation. Simulation results show that the proposed method can train the robots of the robot soccer team effectively, achieving higher role rewards and higher team rewards as compared to other approaches that can be used to solve problems of training cooperative multi-agent.

In this paper we describe a parameterized family of first-order distributed optimization algorithms that enable a network of agents to collaboratively calculate a decision variable that minimizes the sum of cost functions at each agent. These algorithms are self-healing in that their correctness is guaranteed even if they are initialized randomly, agents drop in or out of the network, local cost functions change, or communication packets are dropped. Our algorithms are the first single-Laplacian methods to exhibit all of these characteristics. We achieve self-healing by sacrificing internal stability, a fundamental trade-off for single-Laplacian methods.

Languages are powerful solutions to coordination problems: they provide stable, shared expectations about how the words we say correspond to the beliefs and intentions in our heads. Yet language use in a variable and non-stationary social environment requires linguistic representations to be flexible: old words acquire new ad hoc or partner-specific meanings on the fly. In this paper, we introduce a hierarchical Bayesian theory of convention formation that aims to reconcile the long-standing tension between these two basic observations. More specifically, we argue that the central computational problem of communication is not simply transmission, as in classical formulations, but learning and adaptation over multiple timescales. Under our account, rapid learning within dyadic interactions allows for coordination on partner-specific common ground, while social conventions are stable priors that have been abstracted away from interactions with multiple partners. We present new empirical data alongside simulations showing how our model provides a cognitive foundation for explaining several phenomena that have posed a challenge for previous accounts: (1) the convergence to more efficient referring expressions across repeated interaction with the same partner, (2) the gradual transfer of partner-specific common ground to novel partners, and (3) the influence of communicative context on which conventions eventually form.

We consider the problem of sequentially allocating resources in a censored semi-bandits setup, where the learner allocates resources at each step to the arms and observes loss. The loss depends on two hidden parameters, one specific to the arm but independent of the resource allocation, and the other depends on the allocated resource. More specifically, the loss equals zero for an arm if the resource allocated to it exceeds a constant (but unknown) arm dependent threshold. The goal is to learn a resource allocation that minimizes the expected loss. The problem is challenging because the loss distribution and threshold value of each arm are unknown. We study this setting by establishing its `equivalence' to Multiple-Play Multi-Armed Bandits (MP-MAB) and Combinatorial Semi-Bandits. Exploiting these equivalences, we derive optimal algorithms for our problem setting using known algorithms for MP-MAB and Combinatorial Semi-Bandits. The experiments on synthetically generated data validate the performance guarantees of the proposed algorithms.