Related papers: Fixing Incomplete Value Function Decomposition for…

Multi-agent credit assignment is a fundamental challenge for cooperative multi-agent reinforcement learning (MARL), where a team of agents learn from shared reward signals. The Individual-Global-Max (IGM) condition is a widely used…

Multi-agent reinforcement learning (MARL) requires agents to explore within a vast joint action space to find joint actions that lead to coordination. Existing value-based MARL algorithms commonly rely on random exploration, such as…

Centralised training with decentralised execution is an important setting for cooperative deep multi-agent reinforcement learning due to communication constraints during execution and computational tractability in training. In this paper,…

Value decomposition multi-agent reinforcement learning methods learn the global value function as a mixing of each agent's individual utility functions. Coordination graphs (CGs) represent a higher-order decomposition by incorporating…

In decentralized multi-agent reinforcement learning, agents learning in isolation can lead to relative over-generalization (RO), where optimal joint actions are undervalued in favor of suboptimal ones. This hinders effective coordination in…

Large Language Models (LLMs) have shown remarkable performance in completing various tasks. However, solving complex problems often requires the coordination of multiple agents, raising a fundamental question: how to effectively select and…

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…

Recently, deep multiagent reinforcement learning (MARL) has become a highly active research area as many real-world problems can be inherently viewed as multiagent systems. A particularly interesting and widely applicable class of problems…

Developing scalable and efficient reinforcement learning algorithms for cooperative multi-agent control has received significant attention over the past years. Existing literature has proposed inexact decompositions of local Q-functions…

In cooperative multi-agent systems, agents jointly take actions and receive a team reward instead of individual rewards. In the absence of individual reward signals, credit assignment mechanisms are usually introduced to discriminate the…

Cooperation in multi-agent reinforcement learning (MARL) benefits from inter-agent communication, yet most approaches assume idealized channels and existing value decomposition methods ignore who successfully shared information with whom.…

Many advances in cooperative multi-agent reinforcement learning (MARL) are based on two common design principles: value decomposition and parameter sharing. A typical MARL algorithm of this fashion decomposes a centralized Q-function into…

Training a team to complete a complex task via multi-agent reinforcement learning can be difficult due to challenges such as policy search in a large joint policy space, and non-stationarity caused by mutually adapting agents. To facilitate…

Many large MDPs can be represented compactly using a dynamic Bayesian network. Although the structure of the value function does not retain the structure of the process, recent work has shown that value functions in factored MDPs can often…

The dominant framework for off-policy multi-goal reinforcement learning involves estimating goal conditioned Q-value function. When learning to achieve multiple goals, data efficiency is intimately connected with the generalization of the…

Standard deep reinforcement learning algorithms use a shared representation for the policy and value function, especially when training directly from images. However, we argue that more information is needed to accurately estimate the value…

Cooperative multi-agent reinforcement learning (MARL) commonly adopts centralized training with decentralized execution, where value-factorization methods enforce the individual-global-maximum (IGM) principle so that decentralized greedy…

An important property for lifelong-learning agents is the ability to combine existing skills to solve unseen tasks. In general, however, it is unclear how to compose skills in a principled way. We provide a "recipe" for optimal value…

Many practical reinforcement learning environments have a discrete factored action space that induces a large combinatorial set of actions, thereby posing significant challenges. Existing approaches leverage the regular structure of the…

In many real-world scenarios, a team of agents coordinate with each other to compete against an opponent. The challenge of solving this type of game is that the team's joint action space grows exponentially with the number of agents, which…