We present a novel multi-agent simulator named Multi-Agent eXperimenter (MAX) that is designed to simulate blockchain experiments involving large numbers of agents of different types acting in one or several environments. The architecture of MAX is highly modular, enabling easy addition of new models.

Communication plays a vital role for coordination in Multi-Agent Reinforcement Learning (MARL) systems. However, misaligned agents can exploit other agents' trust and delegated power to the communication medium. In this paper, we propose power regularization as a method to limit the adverse effects of communication by misaligned agents, specifically communication which impairs the performance of cooperative agents. Power is a measure of the influence one agent's actions have over another agent's policy. By introducing power regularization, we aim to allow designers to control or reduce agents' dependency on communication when appropriate, and make them more resilient to performance deterioration due to misuses of communication. We investigate several environments in which power regularization can be a valuable capability for learning different policies that reduce the effect of power dynamics between agents during communication.

Prominent large language models have exhibited human-level performance in many domains, even enabling the derived agents to simulate human and social interactions. While practical works have substantiated the practicability of grounding language agents in sandbox simulation or embodied simulators, current social intelligence benchmarks either stay at the language level or use subjective metrics. In pursuit of a more realistic and objective evaluation, we introduce the Social Tasks in Sandbox Simulation (STSS) benchmark, which assesses language agents \textbf{objectively} at the \textbf{action level} by scrutinizing the goal achievements within the multi-agent simulation. Additionally, we sample conversation scenarios to build a language-level benchmark to provide an economically prudent preliminary evaluation and align with prevailing benchmarks. To gauge the significance of agent architecture, we implement a target-driven planning (TDP) module as an adjunct to the existing agent. Our evaluative findings highlight that the STSS benchmark is challenging for state-of-the-art language agents. Furthermore, it effectively discriminates between distinct language agents, suggesting its usefulness as a benchmark for evaluating both language models and agent architectures.

Effective multi-agent collaboration is imperative for solving complex, distributed problems. In this context, two key challenges must be addressed: first, autonomously identifying optimal objectives for collective outcomes; second, aligning these objectives among agents. Traditional frameworks, often reliant on centralized learning, struggle with scalability and efficiency in large multi-agent systems. To overcome these issues, we introduce a decentralized state-based value learning algorithm that enables agents to independently discover optimal states. Furthermore, we introduce a novel mechanism for multi-agent interaction, wherein less proficient agents follow and adopt policies from more experienced ones, thereby indirectly guiding their learning process. Our theoretical analysis shows that our approach leads decentralized agents to an optimal collective policy. Empirical experiments further demonstrate that our method outperforms existing decentralized state-based and action-based value learning strategies by effectively identifying and aligning optimal objectives.

We investigate the challenge of multi-agent deep reinforcement learning in partially competitive environments, where traditional methods struggle to foster reciprocity-based cooperation. LOLA and POLA agents learn reciprocity-based cooperative policies by differentiation through a few look-ahead optimization steps of their opponent. However, there is a key limitation in these techniques. Because they consider a few optimization steps, a learning opponent that takes many steps to optimize its return may exploit them. In response, we introduce a novel approach, Best Response Shaping (BRS), which differentiates through an opponent approximating the best response, termed the "detective." To condition the detective on the agent's policy for complex games we propose a state-aware differentiable conditioning mechanism, facilitated by a question answering (QA) method that extracts a representation of the agent based on its behaviour on specific environment states. To empirically validate our method, we showcase its enhanced performance against a Monte Carlo Tree Search (MCTS) opponent, which serves as an approximation to the best response in the Coin Game. This work expands the applicability of multi-agent RL in partially competitive environments and provides a new pathway towards achieving improved social welfare in general sum games.

Language significantly influences the formation and evolution of Human emergent behavior, which is crucial in understanding collective intelligence within human societies. Considering that the study of how language affects human behavior needs to put it into the dynamic scenarios in which it is used, we introduce AgentGroupChat in this paper, a simulation that delves into the complex role of language in shaping collective behavior through interactive debate scenarios. Central to this simulation are characters engaging in dynamic conversation interactions. To enable simulation, we introduce the Verbal Strategist Agent, utilizing large language models to enhance interaction strategies by incorporating elements of persona and action. We set four narrative scenarios based on AgentGroupChat to demonstrate the simulation's capacity to mimic complex language use in group dynamics. Evaluations focus on aligning agent behaviors with human expectations and the emergence of collective behaviors within the simulation. Results reveal that emergent behaviors materialize from a confluence of factors: a conducive environment for extensive information exchange, characters with diverse traits, high linguistic comprehension, and strategic adaptability. During discussions on ``the impact of AI on humanity'' in AgentGroupChat simulation, philosophers commonly agreed that ``AI could enhance societal welfare with judicious limitations'' and even come to a conclusion that ``the essence of true intelligence encompasses understanding the necessity to constrain self abilities''. Additionally, in the competitive domain of casting for primary roles in films in AgentGroupChat, certain actors were ready to reduce their remuneration or accept lesser roles, motivated by their deep-seated desire to contribute to the project.

We introduce the Laser Learning Environment (LLE), a collaborative multi-agent reinforcement learning environment in which coordination is central. In LLE, agents depend on each other to make progress (interdependence), must jointly take specific sequences of actions to succeed (perfect coordination), and accomplishing those joint actions does not yield any intermediate reward (zero-incentive dynamics). The challenge of such problems lies in the difficulty of escaping state space bottlenecks caused by interdependence steps since escaping those bottlenecks is not rewarded. We test multiple state-of-the-art value-based MARL algorithms against LLE and show that they consistently fail at the collaborative task because of their inability to escape state space bottlenecks, even though they successfully achieve perfect coordination. We show that Q-learning extensions such as prioritised experience replay and n-steps return hinder exploration in environments with zero-incentive dynamics, and find that intrinsic curiosity with random network distillation is not sufficient to escape those bottlenecks. We demonstrate the need for novel methods to solve this problem and the relevance of LLE as cooperative MARL benchmark.

The rise of multi-agent systems, especially the success of multi-agent reinforcement learning (MARL), is reshaping our future across diverse domains like autonomous vehicle networks. However, MARL still faces significant challenges, particularly in achieving zero-shot scalability, which allows trained MARL models to be directly applied to unseen tasks with varying numbers of agents. In addition, real-world multi-agent systems usually contain agents with different functions and strategies, while the existing scalable MARL methods only have limited heterogeneity. To address this, we propose a novel MARL framework named Scalable and Heterogeneous Proximal Policy Optimization (SHPPO), integrating heterogeneity into parameter-shared PPO-based MARL networks. we first leverage a latent network to adaptively learn strategy patterns for each agent. Second, we introduce a heterogeneous layer for decision-making, whose parameters are specifically generated by the learned latent variables. Our approach is scalable as all the parameters are shared except for the heterogeneous layer, and gains both inter-individual and temporal heterogeneity at the same time. We implement our approach based on the state-of-the-art backbone PPO-based algorithm as SHPPO, while our approach is agnostic to the backbone and can be seamlessly plugged into any parameter-shared MARL method. SHPPO exhibits superior performance over the baselines such as MAPPO and HAPPO in classic MARL environments like Starcraft Multi-Agent Challenge (SMAC) and Google Research Football (GRF), showcasing enhanced zero-shot scalability and offering insights into the learned latent representation's impact on team performance by visualization.

We address the challenge of sampling and remote estimation for autoregressive Markovian processes in a multi-hop wireless network with statistically-identical agents. Agents cache the most recent samples from others and communicate over wireless collision channels governed by an underlying graph topology. Our goal is to minimize time-average estimation error and/or age of information with decentralized scalable sampling and transmission policies, considering both oblivious (where decision-making is independent of the physical processes) and non-oblivious policies (where decision-making depends on physical processes). We prove that in oblivious policies, minimizing estimation error is equivalent to minimizing the age of information. The complexity of the problem, especially the multi-dimensional action spaces and arbitrary network topologies, makes theoretical methods for finding optimal transmission policies intractable. We optimize the policies using a graphical multi-agent reinforcement learning framework, where each agent employs a permutation-equivariant graph neural network architecture. Theoretically, we prove that our proposed framework exhibits desirable transferability properties, allowing transmission policies trained on small- or moderate-size networks to be executed effectively on large-scale topologies. Numerical experiments demonstrate that (i) Our proposed framework outperforms state-of-the-art baselines; (ii) The trained policies are transferable to larger networks, and their performance gains increase with the number of agents; (iii) The training procedure withstands non-stationarity even if we utilize independent learning techniques; and, (iv) Recurrence is pivotal in both independent learning and centralized training and decentralized execution, and improves the resilience to non-stationarity in independent learning.

Cooperative multi-agent reinforcement learning (MARL) has been an increasingly important research topic in the last half-decade because of its great potential for real-world applications. Because of the curse of dimensionality, the popular "centralized training decentralized execution" framework requires a long time in training, yet still cannot converge efficiently. In this paper, we propose a general training framework, MARL-LNS, to algorithmically address these issues by training on alternating subsets of agents using existing deep MARL algorithms as low-level trainers, while not involving any additional parameters to be trained. Based on this framework, we provide three algorithm variants based on the framework: random large neighborhood search (RLNS), batch large neighborhood search (BLNS), and adaptive large neighborhood search (ALNS), which alternate the subsets of agents differently. We test our algorithms on both the StarCraft Multi-Agent Challenge and Google Research Football, showing that our algorithms can automatically reduce at least 10% of training time while reaching the same final skill level as the original algorithm.