Related papers: Descent-Guided Policy Gradient for Scalable Cooper…

Deep Reinforcement Learning (RL) algorithms can solve complex sequential decision tasks successfully. However, they have a major drawback of having poor sample efficiency which can often be tackled by knowledge reuse. In Multi-Agent…

Optimizing communication topology is fundamental to the efficiency and effectiveness of Large Language Model (LLM)-based Multi-Agent Systems (MAS). While recent approaches utilize reinforcement learning to dynamically construct…

Cooperative multi-agent reinforcement learning (MARL) has achieved significant results, most notably by leveraging the representation-learning abilities of deep neural networks. However, large centralized approaches quickly become…

Decentralized multi-agent reinforcement learning (MARL) algorithms have become popular in the literature since it allows heterogeneous agents to have their own reward functions as opposed to canonical multi-agent Markov Decision Process…

Cooperative multi-agent reinforcement learning (MARL) is typically formalised as a Decentralised Partially Observable Markov Decision Process (Dec-POMDP), where agents must reason about the environment and other agents' behaviour. In…

In this paper, we study the problem of robust cooperative multi-agent reinforcement learning (RL) where a large number of cooperative agents with distributed information aim to learn policies in the presence of \emph{stochastic} and…

Multi-agent deep reinforcement learning (MARL) suffers from a lack of commonly-used evaluation tasks and criteria, making comparisons between approaches difficult. In this work, we provide a systematic evaluation and comparison of three…

In networked multi-agent reinforcement learning (Networked-MARL), decentralized agents must act under local observability and constrained communication over fixed physical graphs. Existing methods often assume static neighborhoods, limiting…

Mapping deep neural networks (DNNs) to hardware is critical for optimizing latency, energy consumption, and resource utilization, making it a cornerstone of high-performance accelerator design. Due to the vast and complex mapping space,…

Distributed optimization enables networked agents to cooperatively solve a global optimization problem even with each participating agent only having access to a local partial view of the objective function. Despite making significant…

We present Distributed Deep Deterministic Policy Gradient (3DPG), a multi-agent actor-critic (MAAC) algorithm for Markov games. Unlike previous MAAC algorithms, 3DPG is fully distributed during both training and deployment. 3DPG agents…

Multi-agent reinforcement learning (MARL) has attracted much research attention recently. However, unlike its single-agent counterpart, many theoretical and algorithmic aspects of MARL have not been well-understood. In this paper, we study…

The Sampled Policy Gradient (SPG) algorithm is a new offline actor-critic variant that samples in the action space to approximate the policy gradient. It does so by using the critic to evaluate the sampled actions. SPG offers theoretical…

A challenge in reinforcement learning (RL) is minimizing the cost of sampling associated with exploration. Distributed exploration reduces sampling complexity in multi-agent RL (MARL). We investigate the benefits to performance in MARL when…

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…

Multi-agent reinforcement learning (MARL) has been increasingly explored to learn the cooperative policy towards maximizing a certain global reward. Many existing studies take advantage of graph neural networks (GNN) in MARL to propagate…

This work adopts the very successful distributional perspective on reinforcement learning and adapts it to the continuous control setting. We combine this within a distributed framework for off-policy learning in order to develop what we…

Training a multi-agent reinforcement learning (MARL) algorithm is more challenging than training a single-agent reinforcement learning algorithm, because the result of a multi-agent task strongly depends on the complex interactions among…

Centralised training with decentralised execution (CT-DE) serves as the foundation of many leading multi-agent reinforcement learning (MARL) algorithms. Despite its popularity, it suffers from a critical drawback due to its reliance on…

In the field of cooperative multi-agent reinforcement learning (MARL), the standard paradigm is the use of centralised training and decentralised execution where a central critic conditions the policies of the cooperative agents based on a…