In multi-agent learning, the predominant approach focuses on generalization, often neglecting the optimization of individual agents. This emphasis on generalization limits the ability of agents to utilize their unique strengths, resulting in inefficiencies. This paper introduces Comparative Advantage Maximization (CAM), a method designed to enhance individual agent specialization in multiagent systems. CAM employs a two-phase process, combining centralized population training with individual specialization through comparative advantage maximization. CAM achieved a 13.2% improvement in individual agent performance and a 14.9% increase in behavioral diversity compared to state-of-the-art systems. The success of CAM highlights the importance of individual agent specialization, suggesting new directions for multi-agent system development.

Offline reinforcement learning (RL) has garnered significant attention for its ability to learn effective policies from pre-collected datasets without the need for further environmental interactions. While promising results have been demonstrated in single-agent settings, offline multi-agent reinforcement learning (MARL) presents additional challenges due to the large joint state-action space and the complexity of multi-agent behaviors. A key issue in offline RL is the distributional shift, which arises when the target policy being optimized deviates from the behavior policy that generated the data. This problem is exacerbated in MARL due to the interdependence between agents' local policies and the expansive joint state-action space. Prior approaches have primarily addressed this challenge by incorporating regularization in the space of either Q-functions or policies. In this work, we introduce a regularizer in the space of stationary distributions to better handle distributional shift. Our algorithm, ComaDICE, offers a principled framework for offline cooperative MARL by incorporating stationary distribution regularization for the global learning policy, complemented by a carefully structured multi-agent value decomposition strategy to facilitate multi-agent training. Through extensive experiments on the multi-agent MuJoCo and StarCraft II benchmarks, we demonstrate that ComaDICE achieves superior performance compared to state-of-the-art offline MARL methods across nearly all tasks. Over the years, deep RL has achieved remarkable success in various decision-making tasks (Levine et al., 2016; Silver et al., 2017; Kalashnikov et al., 2018; Haydari & Yılmaz, 2020). However, a significant limitation of deep RL is its need for millions of interactions with the environment to gather experiences for policy improvement.

Reconstructing past events requires reasoning across long time horizons. To figure out what happened, we need to use our prior knowledge about the world and human behavior and draw inferences from various sources of evidence including visual, language, and auditory cues. We introduce MARPLE, a benchmark for evaluating long-horizon inference capabilities using multi-modal evidence. Our benchmark features agents interacting with simulated households, supporting vision, language, and auditory stimuli, as well as procedurally generated environments and agent behaviors. Inspired by classic ``whodunit'' stories, we ask AI models and human participants to infer which agent caused a change in the environment based on a step-by-step replay of what actually happened. The goal is to correctly identify the culprit as early as possible. Our findings show that human participants outperform both traditional Monte Carlo simulation methods and an LLM baseline (GPT-4) on this task. Compared to humans, traditional inference models are less robust and performant, while GPT-4 has difficulty comprehending environmental changes. We analyze what factors influence inference performance and ablate different modes of evidence, finding that all modes are valuable for performance. Overall, our experiments demonstrate that the long-horizon, multimodal inference tasks in our benchmark present a challenge to current models.

Traditional multi-agent path finding (MAPF) methods try to compute entire start-goal paths which are collision free. However, computing an entire path can take too long for MAPF systems where agents need to replan fast. Methods that address this typically employ a "windowed" approach and only try to find collision free paths for a small windowed timestep horizon. This adaptation comes at the cost of incompleteness; all current windowed approaches can become stuck in deadlock or livelock. Our main contribution is to introduce our framework, WinC-MAPF, for Windowed MAPF that enables completeness. Our framework uses heuristic update insights from single-agent real-time heuristic search algorithms as well as agent independence ideas from MAPF algorithms. We also develop Single-Step CBS (SS-CBS), an instantiation of this framework using a novel modification to CBS. We show how SS-CBS, which only plans a single step and updates heuristics, can effectively solve tough scenarios where existing windowed approaches fail.

The growing interest in human-robot collaboration (HRC), where humans and robots cooperate towards shared goals, has seen significant advancements over the past decade. While previous research has addressed various challenges, several key issues remain unresolved. Many domains within HRC involve activities that do not necessarily require human presence throughout the entire task. Existing literature typically models HRC as a closed system, where all agents are present for the entire duration of the task. In contrast, an open model offers flexibility by allowing an agent to enter and exit the collaboration as needed, enabling them to concurrently manage other tasks. In this paper, we introduce a novel multiagent framework called oDec-MDP, designed specifically to model open HRC scenarios where agents can join or leave tasks flexibly during execution. We generalize a recent multiagent inverse reinforcement learning method - Dec-AIRL to learn from open systems modeled using the oDec-MDP. Our method is validated through experiments conducted in both a simplified toy firefighting domain and a realistic dyadic human-robot collaborative assembly. Results show that our framework and learning method improves upon its closed system counterpart.

Despite often being perceived as morally objectionable, stereotypes are a common feature of social groups, a phenomenon that has often been attributed to biased motivations or limits on the ability to process information. We argue that one reason for this continued prevalence is that pre-existing expectations about how others will behave, in the context of social coordination, can change the behaviors of one's social partners, creating the very stereotype one expected to see, even in the absence of other potential sources of stereotyping. We use a computational model of dynamic social coordination to illustrate how this "feedback loop" can emerge, engendering and entrenching stereotypic behavior, and then show that human behavior on the task generates a comparable feedback loop. Notably, people's choices on the task are not related to social dominance or system justification, suggesting biased motivations are not necessary to maintain these stereotypes.

As the field of multi-agent reinforcement learning (MARL) progresses towards larger and more complex environments, achieving strong performance while maintaining memory efficiency and scalability to many agents becomes increasingly important. Although recent research has led to several advanced algorithms, to date, none fully address all of these key properties simultaneously. In this work, we introduce Sable, a novel and theoretically sound algorithm that adapts the retention mechanism from Retentive Networks to MARL. Sable's retention-based sequence modelling architecture allows for computationally efficient scaling to a large number of agents, as well as maintaining a long temporal context, making it well-suited for large-scale partially observable environments. Through extensive evaluations across six diverse environments, we demonstrate how Sable is able to significantly outperform existing state-of-the-art methods in the majority of tasks (34 out of 45, roughly 75%). Furthermore, Sable demonstrates stable performance as we scale the number of agents, handling environments with more than a thousand agents while exhibiting a linear increase in memory usage. Finally, we conduct ablation studies to isolate the source of Sable's performance gains and confirm its efficient computational memory usage. Our results highlight Sable's performance and efficiency, positioning it as a leading approach to MARL at scale. When considering large-scale practical applications of multi-agent reinforcement learning (MARL) such as autonomous driving (Lian & Deshmukh, 2006; Zhou et al., 2021; Li et al., 2022) and electricity grid control (Kamboj et al., 2011; Li et al., 2016), it becomes increasingly important to maintain three key properties for a system to be effective: strong performance, memory efficiency, and scalability to many agents. Although many existing MARL approaches exhibit one or two of these properties, a solution effectively encompassing all three remains elusive. To briefly illustrate our point, we consider the spectrum of approaches to MARL. Such algorithms demonstrate proficiency in handling many agents in a memory efficient way by typically using shared parameters and conditioning on an agent identifier. However, at scale, the performance of fully decentralised methods remains suboptimal compared to more centralised approaches (Papoudakis et al., 2021; Yu et al., 2022; Wen et al., 2022). Between decentralised and centralised methods, lie CTDE approaches (Lowe et al., 2017; Papoudakis et al., 2021; Yu et al., 2022).

The ex ante equilibrium for two-team zero-sum games, where agents within each team collaborate to compete against the opposing team, is known to be the best a team can do for coordination. Many existing works on ex ante equilibrium solutions are aiming to extend the scope of ex ante equilibrium solving to large-scale team games based on Policy Space Response Oracle (PSRO). However, the joint team policy space constructed by the most prominent method, Team PSRO, cannot cover the entire team policy space in heterogeneous team games where teammates play distinct roles. Such insufficient policy expressiveness causes Team PSRO to be trapped into a sub-optimal ex ante equilibrium with significantly higher exploitability and never converges to the global ex ante equilibrium. To find the global ex ante equilibrium without introducing additional computational complexity, we first parameterize heterogeneous policies for teammates, and we prove that optimizing the heterogeneous teammates' policies sequentially can guarantee a monotonic improvement in team rewards. We further propose Heterogeneous-PSRO (H-PSRO), a novel framework for heterogeneous team games, which integrates the sequential correlation mechanism into the PSRO framework and serves as the first PSRO framework for heterogeneous team games. We prove that H-PSRO achieves lower exploitability than Team PSRO in heterogeneous team games. Empirically, H-PSRO achieves convergence in matrix heterogeneous games that are unsolvable by non-heterogeneous baselines. Further experiments reveal that H-PSRO outperforms non-heterogeneous baselines in both heterogeneous team games and homogeneous settings.

Generative Large Language Models have shown impressive in-context learning abilities, performing well across various tasks with just a prompt. Previous melody-to-lyric research has been limited by scarce high-quality aligned data and unclear standard for creativeness. Most efforts focused on general themes or emotions, which are less valuable given current language model capabilities. In tonal contour languages like Mandarin, pitch contours are influenced by both melody and tone, leading to variations in lyric-melody fit. Our study, validated by the Mpop600 dataset, confirms that lyricists and melody writers consider this fit during their composition process. In this research, we developed a multi-agent system that decomposes the melody-to-lyric task into sub-tasks, with each agent controlling rhyme, syllable count, lyric-melody alignment, and consistency. Listening tests were conducted via a diffusion-based singing voice synthesizer to evaluate the quality of lyrics generated by different agent groups.

Cricket, with its intricate strategies and deep history, increasingly captivates a global audience. The Indian Premier League (IPL), epitomizing Twenty20 cricket, showcases talent in a format that lasts just a few hours as opposed to the longer forms of the game. Renowned for its fusion of technology and fan engagement, the IPL stands as the world's most popular cricket league. This study concentrates on Dream11, India's leading fantasy cricket league for IPL, where participants craft virtual teams based on real player performances to compete internationally. Building a winning fantasy team requires navigating various complex factors including player form and match conditions. Traditionally, this has been approached through operations research and machine learning. This research introduces the FanCric framework, an advanced multi-agent system leveraging Large Language Models (LLMs) and a robust orchestration framework to enhance fantasy team selection in cricket. FanCric employs both structured and unstructured data to surpass traditional methods by incorporating sophisticated AI technologies. The analysis involved scrutinizing approximately 12.7 million unique entries from a Dream11 contest, evaluating FanCric's efficacy against the collective wisdom of crowds and a simpler Prompt Engineering approach. Ablation studies further assessed the impact of generating varying numbers of teams. The exploratory findings are promising, indicating that further investigation into FanCric's capabilities is warranted to fully realize its potential in enhancing strategic decision-making using LLMs in fantasy sports and business in general.