English
Related papers

Related papers: Revisiting the Gumbel-Softmax in MADDPG

200 papers

The Gumbel-Max trick is the basis of many relaxed gradient estimators. These estimators are easy to implement and low variance, but the goal of scaling them comprehensively to large combinatorial distributions is still outstanding. Working…

Machine Learning · Statistics 2021-03-02 Max B. Paulus , Dami Choi , Daniel Tarlow , Andreas Krause , Chris J. Maddison

The research of extending deep reinforcement learning (drl) to multi-agent field has solved many complicated problems and made great achievements. However, almost all these studies only focus on discrete or continuous action space and there…

Machine Learning · Computer Science 2022-09-01 Hongzhi Hua , Guixuan Wen , Kaigui Wu

We consider a setting involving $N$ agents, where each agent interacts with an environment modeled as a Markov Decision Process (MDP). The agents' MDPs differ in their reward functions, capturing heterogeneous objectives/tasks. The…

Machine Learning · Computer Science 2024-09-10 Feng Zhu , Robert W. Heath , Aritra Mitra

Although robotic applications increasingly demand versatile and dynamic object handling, most existing techniques are predominantly focused on grasp-based manipulation, limiting their applicability in non-prehensile tasks. To address this…

Robotics · Computer Science 2025-02-25 Hamidreza Raei , Elena De Momi , Arash Ajoudani

Multi-Agent RL or MARL is one of the complex problems in Autonomous Driving literature that hampers the release of fully-autonomous vehicles today. Several simulators have been in iteration after their inception to mitigate the problem of…

Machine Learning · Computer Science 2023-01-24 Ansh Mittal , Aditya Malte

A widely-used actor-critic reinforcement learning algorithm for continuous control, Deep Deterministic Policy Gradients (DDPG), suffers from the overestimation problem, which can negatively affect the performance. Although the…

Machine Learning · Computer Science 2020-10-20 Ling Pan , Qingpeng Cai , Longbo Huang

A multi-agent deep reinforcement learning (MADRL) is a promising approach to challenging problems in wireless environments involving multiple decision-makers (or actors) with high-dimensional continuous action space. In this paper, we…

Information Theory · Computer Science 2021-09-13 Heunchul Lee , Jaeseong Jeong

The paper considers distributed gradient flow (DGF) for multi-agent nonconvex optimization. DGF is a continuous-time approximation of distributed gradient descent that is often easier to study than its discrete-time counterpart. The paper…

Optimization and Control · Mathematics 2020-08-13 Brian Swenson , Ryan Murray , H. Vincent Poor , Soummya Kar

Autocurricular training is an important sub-area of multi-agent reinforcement learning~(MARL) that allows multiple agents to learn emergent skills in an unsupervised co-evolving scheme. The robotics community has experimented autocurricular…

Artificial Intelligence · Computer Science 2023-05-09 Boling Yang , Liyuan Zheng , Lillian J. Ratliff , Byron Boots , Joshua R. Smith

This paper explores multi-scenario optimization on large platforms using multi-agent reinforcement learning (MARL). We address this by treating scenarios like search, recommendation, and advertising as a cooperative, partially observable…

Machine Learning · Computer Science 2024-07-04 Yang Zhao , Chang Zhou , Jin Cao , Yi Zhao , Shaobo Liu , Chiyu Cheng , Xingchen Li

At present, attention mechanism has been widely applied to the fields of deep learning models. Structural models that based on attention mechanism can not only record the relationships between features position, but also can measure the…

Machine Learning · Computer Science 2021-05-12 Xiaolong Wei , LiFang Yang , Xianglin Huang , Gang Cao , Tao Zhulin , Zhengyang Du , Jing An

Multi-agent pathfinding (MAPF) is a common abstraction of multi-robot trajectory planning problems, where multiple homogeneous robots simultaneously move in the shared environment. While solving MAPF optimally has been proven to be NP-hard,…

Artificial Intelligence · Computer Science 2025-07-01 Anton Andreychuk , Konstantin Yakovlev , Aleksandr Panov , Alexey Skrynnik

Multi-step (also called n-step) methods in reinforcement learning (RL) have been shown to be more efficient than the 1-step method due to faster propagation of the reward signal, both theoretically and empirically, in tasks exploiting…

Artificial Intelligence · Computer Science 2020-06-24 Lingheng Meng , Rob Gorbet , Dana Kulić

Exploration of the high-dimensional state action space is one of the biggest challenges in Reinforcement Learning (RL), especially in multi-agent domain. We present a novel technique called Experience Augmentation, which enables a…

Machine Learning · Computer Science 2020-05-21 Zhenhui Ye , Yining Chen , Guanghua Song , Bowei Yang , Shen Fan

The theory of continuous-time reinforcement learning (RL) has progressed rapidly in recent years. While the ultimate objective of RL is typically to learn deterministic control policies, most existing continuous-time RL methods rely on…

Machine Learning · Computer Science 2026-03-17 Ziheng Cheng , Xin Guo , Yufei Zhang

Solving sequential decision prediction problems, including those in imitation learning settings, requires mitigating the problem of covariate shift. The standard approach, DAgger, relies on capturing expert behaviour in all states that the…

Machine Learning · Computer Science 2019-06-20 Paul Budnarain , Renato Ferreira Pinto Junior , Ilan Kogan

The deep reinforcement learning (DRL) based Volt-VAR optimization (VVO) methods have been widely studied for active distribution networks (ADNs). However, most of them lack safety guarantees in terms of power injection uncertainties due to…

Systems and Control · Electrical Eng. & Systems 2024-09-30 Zhengrong Chen , Siyao Cai , A. P. Sakis Meliopoulos

We study finite-time performance of a recently proposed distributed dual subgradient (DDSG) method for convex constrained multi-agent optimization problems. The algorithm enjoys performance guarantees on the last primal iterate, as opposed…

Optimization and Control · Mathematics 2023-07-28 Subhonmesh Bose , Hoa Dinh Nguyen , Haitian Liu , Ye Guo , Thinh T. Doan , Carolyn L. Beck

We consider (stochastic) softmax policy gradient (PG) methods for bandits and tabular Markov decision processes (MDPs). While the PG objective is non-concave, recent research has used the objective's smoothness and gradient domination…

Machine Learning · Computer Science 2024-10-01 Michael Lu , Matin Aghaei , Anant Raj , Sharan Vaswani

In this paper, we propose a new framework, exploiting the multi-agent deep deterministic policy gradient (MADDPG) algorithm, to enable a base station (BS) and user equipment (UE) to come up with a medium access control (MAC) protocol in a…

Information Theory · Computer Science 2022-06-09 Mateus P. Mota , Alvaro Valcarce , Jean-Marie Gorce , Jakob Hoydis