Blame attribution is one of the key aspects of accountable decision making, as it provides means to quantify the responsibility of an agent for a decision making outcome. In this paper, we study blame attribution in the context of cooperative multi-agent sequential decision making. As a particular setting of interest, we focus on cooperative decision making formalized by Multi-Agent Markov Decision Processes (MMDPs), and we analyze different blame attribution methods derived from or inspired by existing concepts in cooperative game theory. We formalize desirable properties of blame attribution in the setting of interest, and we analyze the relationship between these properties and the studied blame attribution methods. Interestingly, we show that some of the well known blame attribution methods, such as Shapley value, are not performance-incentivizing, while others, such as Banzhaf index, may over-blame agents.

Large sequence models (SM) such as GPT series and BERT have displayed outstanding performance and generalization capabilities in natural language process, vision and recently reinforcement learning. A natural follow-up question is how to abstract multi-agent decision making also as an sequence modeling problem and benefit from the prosperous development of the SMs. In this paper, we introduce a novel architecture named Multi-Agent Transformer (MAT) that effectively casts cooperative multi-agent reinforcement learning (MARL) into SM problems wherein the objective is to map agents' observation sequences to agents' optimal action sequences. Our goal is to build the bridge between MARL and SMs so that the modeling power of modern sequence models can be unleashed for MARL. Central to our MAT is an encoder-decoder architecture which leverages the multi-agent advantage decomposition theorem to transform the joint policy search problem into a sequential decision making process; this renders only linear time complexity for multi-agent problems and, most importantly, endows MAT with monotonic performance improvement guarantee.

In multi-agent reinforcement learning, discovering successful collective behaviors is challenging as it requires exploring a joint action space that grows exponentially with the number of agents. While the tractability of independent agent-wise exploration is appealing, this approach fails on tasks that require elaborate group strategies. We argue that coordinating the agents' policies can guide their exploration and we investigate techniques to promote such an inductive bias. We propose two policy regularization methods: TeamReg, which is based on inter-agent action predictability and CoachReg that relies on synchronized behavior selection. We evaluate each approach on four challenging continuous control tasks with sparse rewards that require varying levels of coordination as well as on the discrete action Google Research Football environment.

Mobile robots rely on maps to navigate through an environment. In the absence of any map, the robots must build the map online from partial observations as they move in the environment. Traditional methods build a map using only direct observations. In contrast, humans identify patterns in the observed environment and make informed guesses about what to expect ahead. Modeling these patterns explicitly is difficult due to the complexity of the environments. However, these complex models can be approximated well using learning-based methods in conjunction with large training data. By extracting patterns, robots can use direct observations and predictions of what lies ahead to better navigate an unknown environment. In this dissertation, we present several learning-based methods to equip mobile robots with prediction capabilities for efficient and safer operation. In the first part of the dissertation, we learn to predict using geometrical and structural patterns in the environment. Partially observed maps provide invaluable cues for accurately predicting the unobserved areas. We first demonstrate the capability of general learning-based approaches to model these patterns for a variety of overhead map modalities. Then we employ task-specific learning for faster navigation in indoor environments by predicting 2D occupancy in the nearby regions. This idea is further extended to 3D point cloud representation for object reconstruction. Predicting the shape of the full object from only partial views, our approach paves the way for efficient next-best-view planning. In the second part of the dissertation, we learn to predict using spatiotemporal patterns in the environment. We focus on dynamic tasks such as target tracking and coverage where we seek decentralized coordination between robots. We first show how graph neural networks can be used for more scalable and faster inference.

Agent-based models (ABMs) have long been employed to explore how individual behaviors aggregate into complex societal phenomena in urban space. Unlike black-box predictive models, ABMs excel at explaining the micro-macro linkages that drive such emergent behaviors. The recent rise of Large Language Models (LLMs) has led to the development of LLM agents capable of simulating urban activities with unprecedented realism. However, the extreme high computational cost of LLMs presents significant challenges for scaling up the simulations of LLM agents. To address this problem, we propose OpenCity, a scalable simulation platform optimized for both system and prompt efficiencies. Specifically, we propose a LLM request scheduler to reduce communication overhead by parallelizing requests through IO multiplexing. Besides, we deisgn a "group-and-distill" prompt optimization strategy minimizes redundancy by clustering agents with similar static attributes. Through experiments on six global cities, OpenCity achieves a 600-fold acceleration in simulation time per agent, a 70% reduction in LLM requests, and a 50% reduction in token usage. These improvements enable the simulation of 10,000 agents' daily activities in 1 hour on commodity hardware. Besides, the substantial speedup of OpenCity allows us to establish a urban simulation benchmark for LLM agents for the first time, comparing simulated urban activities with real-world data in 6 major cities around the globe. We believe our OpenCity platform provides a critical infrastructure to harness the power of LLMs for interdisciplinary studies in urban space, fostering the collective efforts of broader research communities. Code repo is available at https://anonymous.4open.science/r/Anonymous-OpenCity-42BD.

In multi-agent reinforcement learning (MARL), parameter sharing is commonly employed to enhance sample efficiency. However, the popular approach of full parameter sharing often leads to homogeneous policies among agents, potentially limiting the performance benefits that could be derived from policy diversity. To address this critical limitation, we introduce \emph{Kaleidoscope}, a novel adaptive partial parameter sharing scheme that fosters policy heterogeneity while still maintaining high sample efficiency. Specifically, Kaleidoscope maintains one set of common parameters alongside multiple sets of distinct, learnable masks for different agents, dictating the sharing of parameters. It promotes diversity among policy networks by encouraging discrepancy among these masks, without sacrificing the efficiencies of parameter sharing. This design allows Kaleidoscope to dynamically balance high sample efficiency with a broad policy representational capacity, effectively bridging the gap between full parameter sharing and non-parameter sharing across various environments. We further extend Kaleidoscope to critic ensembles in the context of actor-critic algorithms, which could help improve value estimations.Our empirical evaluations across extensive environments, including multi-agent particle environment, multi-agent MuJoCo and StarCraft multi-agent challenge v2, demonstrate the superior performance of Kaleidoscope compared with existing parameter sharing approaches, showcasing its potential for performance enhancement in MARL. The code is publicly available at \url{https://github.com/LXXXXR/Kaleidoscope}.

Social conventions are the foundation for social and economic life. As legions of AI agents increasingly interact with each other and with humans, their ability to form shared conventions will determine how effectively they will coordinate behaviors, integrate into society and influence it. Here, we investigate the dynamics of conventions within populations of Large Language Model (LLM) agents using simulated interactions. First, we show that globally accepted social conventions can spontaneously arise from local interactions between communicating LLMs. Second, we demonstrate how strong collective biases can emerge during this process, even when individual agents appear to be unbiased. Third, we examine how minority groups of committed LLMs can drive social change by establishing new social conventions. We show that once these minority groups reach a critical size, they can consistently overturn established behaviors. In all cases, contrasting the experimental results with predictions from a minimal multi-agent model allows us to isolate the specific role of LLM agents. Our results clarify how AI systems can autonomously develop norms without explicit programming and have implications for designing AI systems that align with human values and societal goals.

Recently, model-based agents have achieved better performance than model-free ones using the same computational budget and training time in single-agent environments. However, due to the complexity of multi-agent systems, it is tough to learn the model of the environment. The significant compounding error may hinder the learning process when model-based methods are applied to multi-agent tasks. This paper proposes an implicit model-based multi-agent reinforcement learning method based on value decomposition methods. Under this method, agents can interact with the learned virtual environment and evaluate the current state value according to imagined future states in the latent space, making agents have the foresight.

We present a multi-agent actor-critic method that aims to implicitly address the credit assignment problem under fully cooperative settings. Our key motivation is that credit assignment among agents may not require an explicit formulation as long as (1) the policy gradients derived from a centralized critic carry sufficient information for the decentralized agents to maximize their joint action value through optimal cooperation and (2) a sustained level of exploration is enforced throughout training. Under the centralized training with decentralized execution (CTDE) paradigm, we achieve the former by formulating the centralized critic as a hypernetwork such that a latent state representation is integrated into the policy gradients through its multiplicative association with the stochastic policies; to achieve the latter, we derive a simple technique called adaptive entropy regularization where magnitudes of the entropy gradients are dynamically rescaled based on the current policy stochasticity to encourage consistent levels of exploration. Our algorithm, referred to as LICA, is evaluated on several benchmarks including the multi-agent particle environments and a set of challenging StarCraft II micromanagement tasks, and we show that LICA significantly outperforms previous methods.

We consider the concurrent reinforcement learning problem where n agents simultaneously learn to make decisions in the same environment by sharing experience with each other. Existing works in this emerging area have empirically demonstrated that Thompson sampling (TS) based algorithms provide a particularly attractive alternative for inducing cooperation, because each agent can independently sample a belief environment (and compute a corresponding optimal policy) from the joint posterior computed by aggregating all agents' data, which induces diversity in exploration among agents while benefiting shared experience from all agents. However, theoretical guarantees in this area remain under-explored; in particular, no regret bound is known on TS based concurrent RL algorithms. In this paper, we fill in this gap by considering two settings. In the first, we study the simple finite-horizon episodic RL setting, where TS is naturally adapted into the concurrent setup by having each agent sample from the current joint posterior at the beginning of each episode.