相关论文: A Recipe for Stable Offline Multi-agent Reinforcem…

A reliable critic is central to on-policy actor-critic learning. But it becomes challenging to learn a reliable critic in a multi-agent sparse reward scenario due to two factors: 1) The joint action space grows exponentially with the number…

We study reinforcement learning (RL) in a setting with a network of agents whose states and actions interact in a local manner where the objective is to find localized policies such that the (discounted) global reward is maximized. A…

In multi-agent systems with large number of agents, typically the contribution of each agent to the value of other agents is minimal (e.g., aggregation systems such as Uber, Deliveroo). In this paper, we consider such multi-agent systems…

Multiagent reinforcement learning (MARL) is commonly considered to suffer from non-stationary environments and exponentially increasing policy space. It would be even more challenging when rewards are sparse and delayed over long…

We propose using regularization for Multi-Agent Reinforcement Learning rather than learning explicit cooperative structures called {\em Multi-Agent Regularized Q-learning} (MARQ). Many MARL approaches leverage centralized structures in…

We present Stable-Layers, a reinforcement learning framework that eliminates the need for paired supervision by fine-tuning a pretrained layer decomposition model using only feedback from a vision-language model (VLM). Starting from…

Despite the success of single-agent reinforcement learning, multi-agent reinforcement learning (MARL) remains challenging due to complex interactions between agents. Motivated by decentralized applications such as sensor networks, swarm…

Recently, safe reinforcement learning (RL) with the actor-critic structure for continuous control tasks has received increasing attention. It is still challenging to learn a near-optimal control policy with safety and convergence…

In cooperative multi-agent reinforcement learning (MARL), the environmental stochasticity and uncertainties will increase exponentially when the number of agents increases, which puts hard pressure on how to come up with a compact latent…

Zero-shot coordination problem in multi-agent reinforcement learning (MARL), which requires agents to adapt to unseen agents, has attracted increasing attention. Traditional approaches often rely on the Self-Play (SP) framework to generate…

Recent success in cooperative multi-agent reinforcement learning (MARL) relies on centralized training and policy sharing. Centralized training eliminates the issue of non-stationarity MARL yet induces large communication costs, and policy…

Cooperative multi-agent reinforcement learning (MARL) commonly adopts centralized training with decentralized execution (CTDE), where centralized critics leverage global information to guide decentralized actors. However,…

[Zhang, ICML 2018] provided the first decentralized actor-critic algorithm for multi-agent reinforcement learning (MARL) that offers convergence guarantees. In that work, policies are stochastic and are defined on finite action spaces. We…

Recent advance in deep offline reinforcement learning (RL) has made it possible to train strong robotic agents from offline datasets. However, depending on the quality of the trained agents and the application being considered, it is often…

This work leverages adaptive social learning to estimate partially observable global states in multi-agent reinforcement learning (MARL) problems. Unlike existing methods, the proposed approach enables the concurrent operation of social…

We propose a new framework for multi-agent reinforcement learning (MARL), where the agents cooperate in a time-evolving network with latent community structures and mixed memberships. Unlike traditional neighbor-based or fixed interaction…

Multi-agent reinforcement learning (MARL) has been gaining extensive attention from academia and industries in the past few decades. One of the fundamental problems in MARL is how to evaluate different approaches comprehensively. Most…

Decentralized learning has shown great promise for cooperative multi-agent reinforcement learning (MARL). However, non-stationarity remains a significant challenge in fully decentralized learning. In the paper, we tackle the…

Value decomposition has long been a fundamental technique in multi-agent dynamic programming and reinforcement learning (RL). Specifically, the value function of a global state $(s_1,s_2,\ldots,s_N)$ is often approximated as the sum of…

Training a multi-agent reinforcement learning (MARL) model with a sparse reward is generally difficult because numerous combinations of interactions among agents induce a certain outcome (i.e., success or failure). Earlier studies have…