Large Language Models (LLMs) have increasingly demonstrated the ability to facilitate the development of multi-agent systems that allow the interpretation of thoughts and actions generated by each individual. Promising advancements have also been made in LLM-based interaction with existing worlds, particularly in interacting with simulated environments. This paper aims to integrate both aforementioned topics (agents & world interaction) into a single simulation where multiple agents can work together to solve a problem, modeling how groups of humans can often solve problems better than individuals. By showing whether LLMs demonstrate the synergy of human collaboration, it could lead to advancements in the applications of LLMs. We implemented two simulations: a physical studio apartment with two roommates, and another where agents collaborate to complete a programming task. We provide a multi-agent framework, discuss the performance of the agents in each simulation, and discuss potential future additions.

Autonomous systems often have logical constraints arising, for example, from safety, operational, or regulatory requirements. Such constraints can be expressed using temporal logic specifications. The system state is often partially observable. Moreover, it could encompass a team of multiple agents with a common objective but disparate information structures and constraints. In this paper, we first introduce an optimal control theory for partially observable Markov decision processes (POMDPs) with finite linear temporal logic constraints. We provide a structured methodology for synthesizing policies that maximize a cumulative reward while ensuring that the probability of satisfying a temporal logic constraint is sufficiently high. Our approach comes with guarantees on approximate reward optimality and constraint satisfaction. We then build on this approach to design an optimal control framework for logically constrained multi-agent settings with information asymmetry. We illustrate the effectiveness of our approach by implementing it on several case studies.

Spatial information is essential in various fields. How to explicitly model according to the spatial location of agents is also very important for the multi-agent problem, especially when the number of agents is changing and the scale is enormous. Inspired by the point cloud task in computer vision, we propose a spatial information extraction structure for multi-agent reinforcement learning in this paper. Agents can effectively share the neighborhood and global information through a spatially encoder-decoder structure. Our method follows the centralized training with decentralized execution (CTDE) paradigm. In addition, our structure can be applied to various existing mainstream reinforcement learning algorithms with minor modifications and can deal with the problem with a variable number of agents. The experiments in several multi-agent scenarios show that the existing methods can get convincing results by adding our spatially explicit architecture.

Planning problems are, in general, PSPACE-complete; large problems, especially multi-agent problems with required coordination, can be intractable or impractical to solve. Factored planning and multi-agent planning both address this by separating multi-agent problems into tractable sub-problems, but there are limitations in the expressivity of existing planners and in the ability to handle tightly coupled multi-agent problems. This paper presents EGOPLAN, a framework which factors a multi-agent problem into related sub-problems which are solved by iteratively calling on a single agent planner. EGOPLAN is evaluated on a multi-robot test domain with durative actions, required coordination, and temporal constraints, comparing the performance of a temporal planner, OPTIC-CPLEX, with and without EGOPLAN. Our results show that for our test domain, using EGOPLAN allows OPTIC-CPLEX to solve problems that are twice as complex as it can solve without EGOPLAN, and to solve complex problems significantly faster.

In a warehouse environment, tasks appear dynamically. Consequently, a task management system that matches them with the workforce too early (e.g., weeks in advance) is necessarily sub-optimal. Also, the rapidly increasing size of the action space of such a system consists of a significant problem for traditional schedulers. Reinforcement learning, however, is suited to deal with issues requiring making sequential decisions towards a long-term, often remote, goal. In this work, we set ourselves on a problem that presents itself with a hierarchical structure: the task-scheduling, by a centralised agent, in a dynamic warehouse multi-agent environment and the execution of one such schedule, by decentralised agents with only partial observability thereof. We propose to use deep reinforcement learning to solve both the high-level scheduling problem and the low-level multi-agent problem of schedule execution. Finally, we also conceive the case where centralisation is impossible at test time and workers must learn how to cooperate in executing the tasks in an environment with no schedule and only partial observability.

This paper solves a path planning problem for a group of gliders. The gliders are tasked with visiting a set of interest points. The gliders have limited range but are able to increase their range by visiting special points called thermals. The problem addressed in this paper is of path planning for the gliders such that, the total number of interest points visited by the gliders is maximized. This is referred to as the multi-agent problem. The problem is solved by first decomposing it into several single-agent problems. In a single-agent problem a set of interest points are allocated to a single glider. This problem is solved by planning a path which maximizes the number of visited interest points from the allocated set. This is achieved through a uniform cost graph search, as shown in our earlier work. The multi-agent problem now consists of determining the best allocation (of interest points) for each glider. Two ways are presented of solving this problem, a brute force search approach as shown in earlier work and a Branch\&Bound type graph search. The Branch&Bound approach is the main contribution of the paper. This approach is proven to be optimal and shown to be faster than the brute force search using simulations.

Pitting two artificial intelligences against each other in games such as DeepMind's Go has led to some of the biggest breakthroughs in AI in recent years, as the machines learn skills through trial and error that eventually lead to them beating humans. But can the same technique produce a more useful AI capable of operating in the real word? OpenAI, a San Francisco-based AI research group, published research on Tuesday showing what it claimed was a method for training increasingly powerful smart systems that could prepare them for tackling more ordinary human problems. Set in increasingly realistic environments, the technique points to a way for the AI to "evolve" in a simulated world until it is ready to be used, it said. The researchers used several intelligent "agents" in a game of hide-and-seek played in a simulated physical environment.

We consider the reinforcement learning problem of training multiple agents in order to maximize a shared reward. In this multi-agent system, each agent seeks to maximize the reward while interacting with other agents, and they may or may not be able to communicate. Typically the agents do not have access to other agent policies and thus each agent observes a non-stationary and partially-observable environment. In order to resolve this issue, we demonstrate a novel multi-agent training framework that first turns a multi-agent problem into a single-agent problem to obtain a centralized expert that is then used to guide supervised learning for multiple independent agents with the goal of decentralizing the policy. We additionally demonstrate a way to turn the exponential growth in the joint action space into a linear growth for the centralized policy. Overall, the problem is twofold: the problem of obtaining a centralized expert, and then the problem of supervised learning to train the multi-agents. We demonstrate our solutions to both of these tasks, and show that supervised learning can be used to decentralize a multi-agent policy.

Assistants are all the rage right now. Everyone seems to be working on one. People imagine them becoming the new interface to computers -- why bother with apps and searching the web when you can just ask your assistant to do it for you? Yet, a major challenge stands between the dream assistant and the current reality. It's called the multi-agent problem, and most companies are reluctant to talk about it.