Autocurricular training is an important sub-area of multi-agent reinforcement learning~(MARL) that allows multiple agents to learn emergent skills in an unsupervised co-evolving scheme. The robotics community has experimented autocurricular training with physically grounded problems, such as robust control and interactive manipulation tasks. However, the asymmetric nature of these tasks makes the generation of sophisticated policies challenging. Indeed, the asymmetry in the environment may implicitly or explicitly provide an advantage to a subset of agents which could, in turn, lead to a low-quality equilibrium. This paper proposes a novel game-theoretic algorithm, Stackelberg Multi-Agent Deep Deterministic Policy Gradient (ST-MADDPG), which formulates a two-player MARL problem as a Stackelberg game with one player as the `leader' and the other as the `follower' in a hierarchical interaction structure wherein the leader has an advantage. We first demonstrate that the leader's advantage from ST-MADDPG can be used to alleviate the inherent asymmetry in the environment. By exploiting the leader's advantage, ST-MADDPG improves the quality of a co-evolution process and results in more sophisticated and complex strategies that work well even against an unseen strong opponent.

Federated learning is an important framework in modern machine learning that seeks to integrate the training of learning models from multiple users, each user having their own local data set, in a way that is sensitive to data privacy and to communication loss constraints. In clustered federated learning, one assumes an additional unknown group structure among users, and the goal is to train models that are useful for each group, rather than simply training a single global model for all users. In this paper, we propose a novel solution to the problem of clustered federated learning that is inspired by ideas in consensus-based optimization (CBO). Our new CBO-type method is based on a system of interacting particles that is oblivious to group memberships. Our model is motivated by rigorous mathematical reasoning, including a mean field analysis describing the large number of particles limit of our particle system, as well as convergence guarantees for the simultaneous global optimization of general non-convex objective functions (corresponding to the loss functions of each cluster of users) in the mean-field regime. Experimental results demonstrate the efficacy of our FedCBO algorithm compared to other state-of-the-art methods and help validate our methodological and theoretical work.

Artificial neural networks (ANNs) are increasingly used as research models, but questions remain about their generalizability and representational invariance. Biological neural networks under social constraints evolved to enable communicable representations, demonstrating generalization capabilities. This study proposes a communication protocol between cooperative agents to analyze the formation of individual and shared abstractions and their impact on task performance. This communication protocol aims to mimic language features by encoding high-dimensional information through low-dimensional representation. Using grid-world mazes and reinforcement learning, teacher ANNs pass a compressed message to a student ANN for better task completion. Through this, the student achieves a higher goal-finding rate and generalizes the goal location across task worlds. Further optimizing message content to maximize student reward improves information encoding, suggesting that an accurate representation in the space of messages requires bi-directional input. This highlights the role of language as a common representation between agents and its implications on generalization capabilities.

In the diverse array of work investigating the nature of human values from psychology, philosophy and social sciences, there is a clear consensus that values guide behaviour. More recently, a recognition that values provide a means to engineer ethical AI has emerged. Indeed, Stuart Russell proposed shifting AI's focus away from simply ``intelligence'' towards intelligence ``provably aligned with human values''. This challenge -- the value alignment problem -- with others including an AI's learning of human values, aggregating individual values to groups, and designing computational mechanisms to reason over values, has energised a sustained research effort. Despite this, no formal, computational definition of values has yet been proposed. We address this through a formal conceptual framework rooted in the social sciences, that provides a foundation for the systematic, integrated and interdisciplinary investigation into how human values can support designing ethical AI.

Training a dialogue policy using deep reinforcement learning requires a lot of exploration of the environment. The amount of wasted invalid exploration makes their learning inefficient. In this paper, we find and define an important reason for the invalid exploration: dead-ends. When a conversation enters a dead-end state, regardless of the actions taken afterward, it will continue in a dead-end trajectory until the agent reaches a termination state or maximum turn. We propose a dead-end resurrection (DDR) algorithm that detects the initial dead-end state in a timely and efficient manner and provides a rescue action to guide and correct the exploration direction. To prevent dialogue policies from repeatedly making the same mistake, DDR also performs dialogue data augmentation by adding relevant experiences containing dead-end states. We first validate the dead-end detection reliability and then demonstrate the effectiveness and generality of the method by reporting experimental results on several dialogue datasets from different domains.

Cognitive science aims to identify the principles and mechanisms that underlie adaptive behavior. An important part of this endeavor is the development of unifying, normative theories that specify "design principles" that guide or constrain how intelligent systems respond to their environment [Marr, 1982, Anderson, 1990, Lewis et al., 2014, Griffiths et al., 2015, Gershman et al., 2015]. For example, accounts of learning, cognition, and decision-making often posit a function that an organism is optimizing--e.g., maximizing long-term reward or minimizing prediction error--and test plausible algorithms that achieve this--e.g., a particular learning rule or inference process. Historically, normative theories in cognitive science have been developed in tandem with new formal approaches in computer science and statistics. This partnership has been fruitful even given differences in scientific goals (e.g., engineering artificial intelligence versus reverse-engineering biological intelligence). Normative theories play a key role in facilitating cross-talk between different disciplines by providing a shared set of mathematical, analytical, and conceptual tools for describing computational problems and how to solve them [Ho and Griffiths, 2022]. This paper is written in the spirit of such cross-disciplinary fertilization. Here, we review recent work in computer science [Arumugam and Van Roy, 2021a, 2022] that develops a novel approach for unifying three distinct mathematical frameworks that will be familiar to many cognitive scientists (Figure 1).

One of the major challenges we face with ethical AI today is developing computational systems whose reasoning and behaviour are provably aligned with human values. Human values, however, are notorious for being ambiguous, contradictory and ever-changing. In order to bridge this gap, and get us closer to the situation where we can formally reason about implementing values into AI, this paper presents a formal representation of values, grounded in the social sciences. We use this formal representation to articulate the key challenges for achieving value-aligned behaviour in multiagent systems (MAS) and a research roadmap for addressing them.

In the domain of intelligent transportation systems (ITS), collaborative perception has emerged as a promising approach to overcome the limitations of individual perception by enabling multiple agents to exchange information, thus enhancing their situational awareness. Collaborative perception overcomes the limitations of individual sensors, allowing connected agents to perceive environments beyond their line-of-sight and field of view. However, the reliability of collaborative perception heavily depends on the data aggregation strategy and communication bandwidth, which must overcome the challenges posed by limited network resources. To improve the precision of object detection and alleviate limited network resources, we propose an intermediate collaborative perception solution in the form of a graph attention network (GAT). The proposed approach develops an attention-based aggregation strategy to fuse intermediate representations exchanged among multiple connected agents. This approach adaptively highlights important regions in the intermediate feature maps at both the channel and spatial levels, resulting in improved object detection precision. We propose a feature fusion scheme using attention-based architectures and evaluate the results quantitatively in comparison to other state-of-the-art collaborative perception approaches. Our proposed approach is validated using the V2XSim dataset. The results of this work demonstrate the efficacy of the proposed approach for intermediate collaborative perception in improving object detection average precision while reducing network resource usage.

Metaheuristics are widely recognized gradient-free solvers to hard problems that do not meet the rigorous mathematical assumptions of conventional solvers. The automated design of metaheuristic algorithms provides an attractive path to relieve manual design effort and gain enhanced performance beyond human-made algorithms. However, the specific algorithm prototype and linear algorithm representation in the current automated design pipeline restrict the design within a fixed algorithm structure, which hinders discovering novelties and diversity across the metaheuristic family. To address this challenge, this paper proposes a general framework, AutoOpt, for automatically designing metaheuristic algorithms with diverse structures. AutoOpt contains three innovations: (i) A general algorithm prototype dedicated to covering the metaheuristic family as widely as possible. It promotes high-quality automated design on different problems by fully discovering potentials and novelties across the family. (ii) A directed acyclic graph algorithm representation to fit the proposed prototype. Its flexibility and evolvability enable discovering various algorithm structures in a single run of design, thus boosting the possibility of finding high-performance algorithms. (iii) A graph representation embedding method offering an alternative compact form of the graph to be manipulated, which ensures AutoOpt's generality. Experiments on numeral functions and real applications validate AutoOpt's efficiency and practicability.

This article introduces a modeling framework to characterize evacuee response to environmental stimuli during emergency egress. The model is developed in consistency with stress theory, which explains how an organism reacts to environmental stressors. We integrate the theory into the well-known social-force model, and develop a framework to simulate crowd evacuation behavior in multi-compartment buildings. Our method serves as a theoretical basis to study crowd movement at bottlenecks, and simulate their herding and way-finding behavior in normal and hazardous conditions. The pre-movement behavior is also briefly investigated by using opinion dynamics. The algorithms have been partly tested in FDS+EVAC as well as our simulation platform crowdEgress.