The standard problem setting in cooperative multi-agent settings is self-play (SP), where the goal is to train a team of agents that works well together. However, optimal SP policies commonly contain arbitrary conventions ("handshakes") and are not compatible with other, independently trained agents or humans. This latter desiderata was recently formalized by Hu et al. 2020 as the zero-shot coordination (ZSC) setting and partially addressed with their Other-Play (OP) algorithm, which showed improved ZSC and human-AI performance in the card game Hanabi. OP assumes access to the symmetries of the environment and prevents agents from breaking these in a mutually incompatible way during training. However, as the authors point out, discovering symmetries for a given environment is a computationally hard problem. Instead, we show that through a simple adaption of k-level reasoning (KLR) Costa Gomes et al. 2006, synchronously training all levels, we can obtain competitive ZSC and ad-hoc teamplay performance in Hanabi, including when paired with a human-like proxy bot. We also introduce a new method, synchronous-k-level reasoning with a best response (SyKLRBR), which further improves performance on our synchronous KLR by co-training a best response.

Investigating cooperativity of interlocutors is central in studying pragmatics of dialogue. Models of conversation that only assume cooperative agents fail to explain the dynamics of strategic conversations. Thus, we investigate the ability of agents to identify non-cooperative interlocutors while completing a concurrent visual-dialogue task. Within this novel setting, we study the optimality of communication strategies for achieving this multi-task objective. We use the tools of learning theory to develop a theoretical model for identifying non-cooperative interlocutors and apply this theory to analyze different communication strategies. We also introduce a corpus of non-cooperative conversations about images in the GuessWhat?! dataset proposed by De Vries et al. (2017). We use reinforcement learning to implement multiple communication strategies in this context and find empirical results validate our theory.

The theory of learning in games has extensively studied situations where agents respond dynamically to each other by optimizing a fixed utility function. However, in real situations, the strategic environment varies as a result of past agent choices. Unfortunately, the analysis techniques that enabled a rich characterization of the emergent behavior in static environment games fail to cope with dynamic environment games. To address this, we develop a general framework using probabilistic couplings to extend the analysis of static environment games to dynamic ones. Using this approach, we obtain sufficient conditions under which traditional characterizations of Nash equilibria with best response dynamics and stochastic stability with log-linear learning can be extended to dynamic environment games. As a case study, we pose a model of cyber threat intelligence sharing between firms and a simple dynamic game-theoretic model of social precautions in an epidemic, both of which feature dynamic environments. For both examples, we obtain conditions under which the emergent behavior is characterized in the dynamic game by performing the traditional analysis on a reference static environment game.

In this work, we integrate `social' interactions into the MARL setup through a user-defined relational network and examine the effects of agent-agent relations on the rise of emergent behaviors. Leveraging insights from sociology and neuroscience, our proposed framework models agent relationships using the notion of Reward-Sharing Relational Networks (RSRN), where network edge weights act as a measure of how much one agent is invested in the success of (or `cares about') another. We construct relational rewards as a function of the RSRN interaction weights to collectively train the multi-agent system via a multi-agent reinforcement learning algorithm. The performance of the system is tested for a 3-agent scenario with different relational network structures (e.g., self-interested, communitarian, and authoritarian networks). Our results indicate that reward-sharing relational networks can significantly influence learned behaviors. We posit that RSRN can act as a framework where different relational networks produce distinct emergent behaviors, often analogous to the intuited sociological understanding of such networks.

In this paper, we propose a novel benchmark called the StarCraft Multi-Agent Challenges+, where agents learn to perform multi-stage tasks and to use environmental factors without precise reward functions. The previous challenges (SMAC) recognized as a standard benchmark of Multi-Agent Reinforcement Learning are mainly concerned with ensuring that all agents cooperatively eliminate approaching adversaries only through fine manipulation with obvious reward functions. This challenge, on the other hand, is interested in the exploration capability of MARL algorithms to efficiently learn implicit multi-stage tasks and environmental factors as well as micro-control. This study covers both offensive and defensive scenarios. In the offensive scenarios, agents must learn to first find opponents and then eliminate them. The defensive scenarios require agents to use topographic features. For example, agents need to position themselves behind protective structures to make it harder for enemies to attack. We investigate MARL algorithms under SMAC+ and observe that recent approaches work well in similar settings to the previous challenges, but misbehave in offensive scenarios. Additionally, we observe that an enhanced exploration approach has a positive effect on performance but is not able to completely solve all scenarios. This study proposes new directions for future research.

Due to the COVID-19 pandemic, the global supply chain is disrupted at an unprecedented scale under uncertain and unknown trends of labor shortage, high material prices, and changing travel or trade regulations. To stay competitive, enterprises desire agile and dynamic response strategies to quickly react to disruptions and recover supply-chain functions. Although both centralized and multi-agent approaches have been studied, their implementation requires prior knowledge of disruptions and agent-rule-based reasoning. In this paper, we introduce a model-based multi-agent framework that enables agent coordination and dynamic agent decision-making to respond to supply chain disruptions in an agile and effective manner. Through a small-scale simulated case study, we showcase the feasibility of the proposed approach under several disruption scenarios that affect a supply chain network differently, and analyze performance trade-offs between the proposed distributed and centralized methods.

With the increasing popularity of food delivery platforms, it has become pertinent to look into the working conditions of the 'gig' workers in these platforms, especially providing them fair wages, reasonable working hours, and transparency on work availability. However, any solution to these problems must not degrade customer experience and be cost-effective to ensure that platforms are willing to adopt them. We propose WORK4FOOD, which provides income guarantees to delivery agents, while minimizing platform costs and ensuring customer satisfaction. WORK4FOOD ensures that the income guarantees are met in such a way that it does not lead to increased working hours or degrade environmental impact. To incorporate these objectives, WORK4FOOD balances supply and demand by controlling the number of agents in the system and providing dynamic payment guarantees to agents based on factors such as agent location, ratings, etc. We evaluate WORK4FOOD on a real-world dataset from a leading food delivery platform and establish its advantages over the state of the art in terms of the multi-dimensional objectives at hand.

As the industry of autonomous driving grows, so does the potential interaction of groups of autonomous cars. Combined with the advancement of Artificial Intelligence and simulation, such groups can be simulated, and safety-critical models can be learned controlling the cars within. This study applies reinforcement learning to the problem of multi-agent car parking, where groups of cars aim to efficiently park themselves, while remaining safe and rational. Utilising robust tools and machine learning frameworks, we design and implement a flexible car parking environment in the form of a Markov decision process with independent learners, exploiting multi-agent communication. We implement a suite of tools to perform experiments at scale, obtaining models parking up to 7 cars with over a 98.1% success rate, significantly beating existing single-agent models. We also obtain several results relating to competitive and collaborative behaviours exhibited by the cars in our environment, with varying densities and levels of communication. Notably, we discover a form of collaboration that cannot arise without competition, and a 'leaky' form of collaboration whereby agents collaborate without sufficient state. Such work has numerous potential applications in the autonomous driving and fleet management industries, and provides several useful techniques and benchmarks for the application of reinforcement learning to multi-agent car parking.

We examine how wealth inequality and diversity in the perception of risk of a collective disaster impact cooperation levels in the context of a public goods game with uncertain and non-linear returns. In this game, individuals face a collective-risk dilemma where they may contribute or not to a common pool to reduce their chances of future losses. We draw our conclusions based on social simulations with populations of independent reinforcement learners with diverse levels of risk and wealth. We find that both wealth inequality and diversity in risk assessment can hinder cooperation and augment collective losses. Additionally, wealth inequality further exacerbates long term inequality, causing rich agents to become richer and poor agents to become poorer. On the other hand, diversity in risk only amplifies inequality when combined with bias in group assortment--i.e., high probability that agents from the same risk class play together. Our results also suggest that taking wealth inequality into account can help to design effective policies aiming at leveraging cooperation in large group sizes, a configuration where collective action is harder to achieve. Finally, we characterize the circumstances under which risk perception alignment is crucial and those under which reducing wealth inequality constitutes a deciding factor for collective welfare.

Cooperative multi-agent reinforcement learning (MARL) is making rapid progress for solving tasks in a grid world and real-world scenarios, in which agents are given different attributes and goals, resulting in different behavior through the whole multi-agent task. In this study, we quantify the agent's behavior difference and build its relationship with the policy performance via {\bf Role Diversity}, a metric to measure the characteristics of MARL tasks. We define role diversity from three perspectives: action-based, trajectory-based, and contribution-based to fully measure a multi-agent task. Through theoretical analysis, we find that the error bound in MARL can be decomposed into three parts that have a strong relation to the role diversity. The decomposed factors can significantly impact policy optimization on three popular directions including parameter sharing, communication mechanism, and credit assignment. The main experimental platforms are based on {\bf Multiagent Particle Environment (MPE)} and {\bf The StarCraft Multi-Agent Challenge (SMAC). Extensive experiments} clearly show that role diversity can serve as a robust measurement for the characteristics of a multi-agent cooperation task and help diagnose whether the policy fits the current multi-agent system for a better policy performance.