paper-with-me

홈 › Papers

Revisiting the Gumbel-Softmax in MADDPG

2023-02-23 · Callum Rhys Tilbury, Filippos Christianos, Stefano V. Albrecht

MADDPG is an algorithm in multi-agent reinforcement learning (MARL) that extends the popular single-agent method, DDPG, to multi-agent scenarios. Importantly, DDPG is an algorithm designed for continuous action spaces, where the gradient of the state-action value function exists. For this algorithm to work in discrete action spaces, discrete gradient estimation must be performed. For MADDPG, the Gumbel-Softmax (GS) estimator is used -- a reparameterisation which relaxes a discrete distribution into a similar continuous one. This method, however, is statistically biased, and a recent MARL benchmarking paper suggests that this bias makes MADDPG perform poorly in grid-world situations, where the action space is discrete. Fortunately, many alternatives to the GS exist, boasting a wide range of properties. This paper explores several of these alternatives and integrates them into MADDPG for discrete grid-world scenarios. The corresponding impact on various performance metrics is then measured and analysed. It is found that one of the proposed estimators performs significantly better than the original GS in several tasks, achieving up to 55% higher returns, along with faster convergence.

📄 PDF Abstract BibTeX arXiv:2302.11793

Code (1)

uoe-agents/revisiting-maddpg 공식 구현 pytorch

Tasks

BenchmarkingMulti-agent Reinforcement Learning

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…
Weight Decay 설명 없음
Adam 설명 없음
MADDPG MADDPG, or Multi-agent DDPG, extends DDPG into a multi-agent policy gradient algorithm where decentralized agents learn a…
Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

Invertible Gaussian Reparameterization: Revisiting the Gumbel-Softmax

2019-12-19 · NeurIPS 2020 12 · Andres Potapczynski, Gabriel Loaiza-Ganem, John P. Cunningham

The Gumbel-Softmax is a continuous distribution over the simplex that is often used as a relaxation of discrete distributions. Because it can be readily interpreted and easily reparameterized, it enjoys widespread use. W…

GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution

2016-11-12 · Matt J. Kusner, José Miguel Hernández-Lobato

Generative Adversarial Networks (GAN) have limitations when the goal is to generate sequences of discrete elements. The reason for this is that samples from a distribution on discrete objects such as the multinomial are …

TRIDENT: Breaking the Hybrid-Safety-Physics Coupling for Provably Safe Multi-Agent Reinforcement Learning

2026-06-16 · Zijie Meng, Ziwei Li, Yufei Liu, Zhiyu Li 외 arxiv

Safe coordination in networked cyber-physical systems forces learning algorithms to simultaneously handle hybrid discrete-continuous actions, hard training-time safety constraints, and physics-governed dynamics. We show …

Multi-agent Reinforcement Learning

Gumbel-MPNN: Graph Rewiring with Gumbel-Softmax

2025-08-24 · Marcel Hoffmann, Lukas Galke, Ansgar Scherp arxiv

Graph homophily has been considered an essential property for message-passing neural networks (MPNN) in node classification. Recent findings suggest that performance is more closely tied to the consistency of neighborhoo…

Node Classification

Gumbel-Softmax Flow Matching with Straight-Through Guidance for Controllable Biological Sequence Generation

2025-03-21 · Sophia Tang, Yinuo Zhang, Alexander Tong, Pranam Chatterjee

Flow matching in the continuous simplex has emerged as a promising strategy for DNA sequence design, but struggles to scale to higher simplex dimensions required for peptide and protein generation. We introduce Gumbel-So…