Related papers: ROMA-iQSS: An Objective Alignment Approach via Sta…
Inspired by biological swarms, robotic swarms are envisioned to solve real-world problems that are difficult for individual agents. Biological swarms can achieve collective intelligence based on local interactions and simple rules; however,…
We study the problem of online learning in competitive settings in the context of two-sided matching markets. In particular, one side of the market, the agents, must learn about their preferences over the other side, the firms, through…
In the paradigm of decentralized learning, a group of agents collaborate to learn a global model using a distributed dataset without a central server; nevertheless, it is severely challenged by the heterogeneity of the data distribution…
We present a framework combining hierarchical and multi-agent deep reinforcement learning approaches to solve coordination problems among a multitude of agents using a semi-decentralized model. The framework extends the multi-agent learning…
LLM alignment has progressed in single-agent settings through paradigms such as RL with human feedback (RLHF), while recent work explores scalable alternatives such as RL with AI feedback (RLAIF) and dynamic alignment objectives. However,…
In many real-world settings, a team of agents must coordinate its behaviour while acting in a decentralised fashion. At the same time, it is often possible to train the agents in a centralised fashion where global state information is…
Stochastic games are a popular framework for studying multi-agent reinforcement learning (MARL). Recent advances in MARL have focused primarily on games with finitely many states. In this work, we study multi-agent learning in stochastic…
Many recent successful off-policy multi-agent reinforcement learning (MARL) algorithms for cooperative partially observable environments focus on finding factorized value functions, leading to convoluted network structures. Building on the…
We study distributed algorithms for solving global optimization problems in which the objective function is the sum of local objective functions of agents and the constraint set is given by the intersection of local constraint sets of…
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…
During the past two decades, multi-agent optimization problems have drawn increased attention from the research community. When multiple objective functions are present among agents, many works optimize the sum of these objective functions.…
Information exchange in multi-agent systems improves the cooperation among agents, especially in partially observable settings. In the real world, communication is often carried out over imperfect channels. This requires agents to handle…
We present a multi-agent learning algorithm, ALMA-Learning, for efficient and fair allocations in large-scale systems. We circumvent the traditional pitfalls of multi-agent learning (e.g., the moving target problem, the curse of…
Agent-based models (ABMs) have shown promise for modelling various real world phenomena incompatible with traditional equilibrium analysis. However, a critical concern is the manual definition of behavioural rules in ABMs. Recent…
Challenges in real-world robotic applications often stem from managing multiple, dynamically varying entities such as neighboring robots, manipulable objects, and navigation goals. Existing multi-agent control strategies face scalability…
Multi-agent path finding in formation has many potential real-world applications like mobile warehouse robots. However, previous multi-agent path finding (MAPF) methods hardly take formation into consideration. Furthermore, they are usually…
The objective of meta-learning is to exploit the knowledge obtained from observed tasks to improve adaptation to unseen tasks. As such, meta-learners are able to generalize better when they are trained with a larger number of observed tasks…
Cooperative multi-agent tasks require agents to deduce their own contributions with shared global rewards, known as the challenge of credit assignment. General methods for policy based multi-agent reinforcement learning to solve the…
In the case of the two-person zero-sum stochastic game with a central controller, this paper proposes a best collaborative behavior search and selection algorithm based on reinforcement learning, in response to how to choose the best…
Value-alignment in normative multi-agent systems is used to promote a certain value and to ensure the consistent behaviour of agents in autonomous intelligent systems with human values. However, the current literature is limited to the…