Multi-agent reinforcement learning (MARL) has witnessed a remarkable surge in interest, fueled by the empirical success achieved in applications of single-agent reinforcement learning (RL). In this study, we consider a distributed Q-learning scenario, wherein a number of agents cooperatively solve a sequential decision making problem without access to the central reward function which is an average of the local rewards.

Multi-agent reinforcement learning (MARL) has exploded in popularity in recent years. Many approaches have been developed but they can be divided into three main types: centralized training and execution (CTE), centralized training for decentralized execution (CTDE), and Decentralized training and execution (DTE).Decentralized training and execution methods make the fewest assumptions and are often simple to implement. In fact, as I'll discuss, any single-agent RL method can be used for DTE by just letting each agent learn separately. Of course, there are pros and cons to such approaches as I discuss below. It is worth noting that DTE is required if no offline coordination is available. That is, if all agents must learn during online interactions without prior coordination, learning and execution must both be decentralized. DTE methods can be applied in cooperative, competitive, or mixed cases but this text will focus on the cooperative MARL case. In this text, I will first give a brief description of the cooperative MARL problem in the form of the Dec-POMDP. Then, I will discuss value-based DTE methods starting with independent Q-learning and its extensions and then discuss the extension to the deep case with DQN, the additional complications this causes, and methods that have been developed to (attempt to) address these issues. Next, I will discuss policy gradient DTE methods starting with independent REINFORCE (i.e., vanilla policy gradient), and then extending to the actor-critic case and deep variants (such as independent PPO). Finally, I will discuss some general topics related to DTE and future directions.

We propose a multi-agent system that enables groups of agents to collaborate and work autonomously to execute tasks. Groups can work in a decentralized manner and can adapt to dynamic changes in the environment. Groups of agents solve assigned tasks by exploring the solution space cooperatively based on the highest reward first. The tasks have a dependency structure associated with them. We rigorously evaluated the performance of the system and the individual group performance using centralized and decentralized control approaches for task distribution. Based on the results, the centralized approach is more efficient for systems with a less-dependent system $G_{18}$ (a well-known program graph that contains $18$ nodes with few links), while the decentralized approach performs better for systems with a highly-dependent system $G_{40}$ (a program graph that contains $40$ highly interlinked nodes). We also evaluated task allocation to groups that do not have interdependence. Our findings reveal that there was significantly less difference in the number of tasks allocated to each group in a less-dependent system than in a highly-dependent one. The experimental results showed that a large number of small-size cooperative groups of agents unequivocally improved the system's performance compared to a small number of large-size cooperative groups of agents. Therefore, it is essential to identify the optimal group size for a system to enhance its performance.

Social norms play a crucial role in guiding agents towards understanding and adhering to standards of behavior, thus reducing social conflicts within multi-agent systems (MASs). However, current LLM-based (or generative) MASs lack the capability to be normative. In this paper, we propose a novel architecture, named CRSEC, to empower the emergence of social norms within generative MASs. Our architecture consists of four modules: Creation & Representation, Spreading, Evaluation, and Compliance. This addresses several important aspects of the emergent processes all in one: (i) where social norms come from, (ii) how they are formally represented, (iii) how they spread through agents' communications and observations, (iv) how they are examined with a sanity check and synthesized in the long term, and (v) how they are incorporated into agents' planning and actions. Our experiments deployed in the Smallville sandbox game environment demonstrate the capability of our architecture to establish social norms and reduce social conflicts within generative MASs. The positive outcomes of our human evaluation, conducted with 30 evaluators, further affirm the effectiveness of our approach. Our project can be accessed via the following link: https://github.com/sxswz213/CRSEC.

From its inception, AI has had a rather ambivalent relationship with humans -- swinging between their augmentation and replacement. Now, as AI technologies enter our everyday lives at an ever increasing pace, there is a greater need for AI systems to work synergistically with humans. One critical requirement for such synergistic human-AI interaction is that the AI systems be explainable to the humans in the loop. To do this effectively, AI agents need to go beyond planning with their own models of the world, and take into account the mental model of the human in the loop. Drawing from several years of research in our lab, we will discuss how the AI agent can use these mental models to either conform to human expectations, or change those expectations through explanatory communication. While the main focus of the book is on cooperative scenarios, we will point out how the same mental models can be used for obfuscation and deception. Although the book is primarily driven by our own research in these areas, in every chapter, we will provide ample connections to relevant research from other groups.

Decision-making problems, categorized as single-agent, e.g., Atari, cooperative multi-agent, e.g., Hanabi, competitive multi-agent, e.g., Hold'em poker, and mixed cooperative and competitive, e.g., football, are ubiquitous in the real world. Various methods are proposed to address the specific decision-making problems. Despite the successes in specific categories, these methods typically evolve independently and cannot generalize to other categories. Therefore, a fundamental question for decision-making is: \emph{Can we develop \textbf{a single algorithm} to tackle \textbf{ALL} categories of decision-making problems?} There are several main challenges to address this question: i) different decision-making categories involve different numbers of agents and different relationships between agents, ii) different categories have different solution concepts and evaluation measures, and iii) there lacks a comprehensive benchmark covering all the categories. This work presents a preliminary attempt to address the question with three main contributions. i) We propose the generalized mirror descent (GMD), a generalization of MD variants, which considers multiple historical policies and works with a broader class of Bregman divergences. ii) We propose the configurable mirror descent (CMD) where a meta-controller is introduced to dynamically adjust the hyper-parameters in GMD conditional on the evaluation measures. iii) We construct the \textsc{GameBench} with 15 academic-friendly games across different decision-making categories. Extensive experiments demonstrate that CMD achieves empirically competitive or better outcomes compared to baselines while providing the capability of exploring diverse dimensions of decision making.

Social robot navigation algorithms are often demonstrated in overly simplified scenarios, prohibiting the extraction of practical insights about their relevance to real world domains. Our key insight is that an understanding of the inherent complexity of a social robot navigation scenario could help characterize the limitations of existing navigation algorithms and provide actionable directions for improvement. Through an exploration of recent literature, we identify a series of factors contributing to the complexity of a scenario, disambiguating between contextual and robot-related ones. We then conduct a simulation study investigating how manipulations of contextual factors impact the performance of a variety of navigation algorithms. We find that dense and narrow environments correlate most strongly with performance drops, while the heterogeneity of agent policies and directionality of interactions have a less pronounced effect. This motivates a shift towards developing and testing algorithms under higher-complexity settings.

Automated testing of computer games is a challenging problem, especially when lengthy scenarios have to be tested. Automating such a scenario boils down to finding the right sequence of interactions given an abstract description of the scenario. Recent works have shown that an agent-based approach works well for the purpose, e.g. due to agents' reactivity, hence enabling a test agent to immediately react to game events and changing state. Many games nowadays are multi-player. This opens up an interesting possibility to deploy multiple cooperative test agents to test such a game, for example to speed up the execution of multiple testing tasks. This paper offers a cooperative multi-agent testing approach and a study of its performance based on a case study on a 3D game called Lab Recruits.

Value function factorization methods are commonly used in cooperative multi-agent reinforcement learning, with QMIX receiving significant attention. Many QMIX-based methods introduce monotonicity constraints between the joint action value and individual action values to achieve decentralized execution. However, such constraints limit the representation capacity of value factorization, restricting the joint action values it can represent and hindering the learning of the optimal policy. To address this challenge, we propose the Potentially Optimal joint actions Weighted QMIX (POWQMIX) algorithm, which recognizes the potentially optimal joint actions and assigns higher weights to the corresponding losses of these joint actions during training. We theoretically prove that with such a weighted training approach the optimal policy is guaranteed to be recovered. Experiments in matrix games, predator-prey, and StarCraft II Multi-Agent Challenge environments demonstrate that our algorithm outperforms the state-of-the-art value-based multi-agent reinforcement learning methods.

Real-time Internet of Things (IoT) applications require real-time support to handle the ever-growing demand for computing resources to process IoT workloads. Fog Computing provides high availability of such resources in a distributed manner. However, these resources must be efficiently managed to distribute unpredictable traffic demands among heterogeneous Fog resources. This paper proposes a fully distributed load-balancing solution with Multi-Agent Reinforcement Learning (MARL) that intelligently distributes IoT workloads to optimize the waiting time while providing fair resource utilization in the Fog network. These agents use transfer learning for life-long self-adaptation to dynamic changes in the environment. By leveraging distributed decision-making, MARL agents effectively minimize the waiting time compared to a single centralized agent solution and other baselines, enhancing end-to-end execution delay. Besides performance gain, a fully distributed solution allows for a global-scale implementation where agents can work independently in small collaboration regions, leveraging nearby local resources. Furthermore, we analyze the impact of a realistic frequency to observe the state of the environment, unlike the unrealistic common assumption in the literature of having observations readily available in real-time for every required action. The findings highlight the trade-off between realism and performance using an interval-based Gossip-based multi-casting protocol against assuming real-time observation availability for every generated workload.