中文
相关论文

相关论文: A Centralised Soft Actor Critic Deep Reinforcement…

200 篇论文

Most prior approaches to offline reinforcement learning (RL) utilize \textit{behavior regularization}, typically augmenting existing off-policy actor critic algorithms with a penalty measuring divergence between the policy and the offline…

机器学习 · 计算机科学 2021-10-15 Haoran Xu , Xianyuan Zhan , Jianxiong Li , Honglei Yin

In federated learning (FL), model aggregation has been widely adopted for data privacy. In recent years, assigning different weights to local models has been used to alleviate the FL performance degradation caused by differences between…

机器学习 · 计算机科学 2022-02-01 Chenghao Huang , Weilong Chen , Yuxi Chen , Shunji Yang , Yanru Zhang

To integrate high amounts of renewable energy resources, electrical power grids must be able to cope with high amplitude, fast timescale variations in power generation. Frequency regulation through demand response has the potential to…

多智能体系统 · 计算机科学 2023-01-09 Vincent Mai , Philippe Maisonneuve , Tianyu Zhang , Hadi Nekoei , Liam Paull , Antoine Lesage-Landry

Deep reinforcement learning (RL) has achieved remarkable success, yet its deployment in real-world scenarios is often limited by vulnerability to environmental uncertainties. Distributionally robust RL (DR-RL) algorithms have been proposed…

机器学习 · 计算机科学 2026-04-21 Mingxuan Cui , Duo Zhou , Yuxuan Han , Grani A. Hanasusanto , Qiong Wang , Huan Zhang , Zhengyuan Zhou

Heating, ventilation, and air conditioning (HVAC) systems are well proved to be capable to provide operating reserve for power systems. As a type of large-capacity and energy-efficient HVAC system (up to 100 MW), district cooling system…

系统与控制 · 电气工程与系统科学 2021-12-22 Peipei Yu , Hongxun Hui , Hongcai Zhang , Ge Chen , Yonghua Song

To widen their accessibility and increase their utility, intelligent agents must be able to learn complex behaviors as specified by (non-expert) human users. Moreover, they will need to learn these behaviors within a reasonable amount of…

机器学习 · 计算机科学 2019-02-13 Dilip Arumugam , Jun Ki Lee , Sophie Saskin , Michael L. Littman

We propose a novel framework to solve risk-sensitive reinforcement learning (RL) problems where the agent optimises time-consistent dynamic spectral risk measures. Based on the notion of conditional elicitability, our methodology constructs…

机器学习 · 计算机科学 2023-05-02 Anthony Coache , Sebastian Jaimungal , Álvaro Cartea

This paper describes how domain knowledge of power system operators can be integrated into reinforcement learning (RL) frameworks to effectively learn agents that control the grid's topology to prevent thermal cascading. Typical RL-based…

系统与控制 · 电气工程与系统科学 2021-12-21 Amarsagar Reddy Ramapuram Matavalam , Kishan Prudhvi Guddanti , Yang Weng , Venkataramana Ajjarapu

The rise of microgrid-based architectures is heavily modifying the energy control landscape in distribution systems making distributed control mechanisms necessary to ensure reliable power system operations. In this paper, we propose the…

系统与控制 · 电气工程与系统科学 2020-10-14 Sergio Rozada , Dimitra Apostolopoulou , Eduardo Alonso

To make efficient use of limited spectral resources, we in this work propose a deep actor-critic reinforcement learning based framework for dynamic multichannel access. We consider both a single-user case and a scenario in which multiple…

机器学习 · 计算机科学 2019-08-23 Chen Zhong , Ziyang Lu , M. Cenk Gursoy , Senem Velipasalar

Object navigation is defined as navigating to an object of a given label in a complex, unexplored environment. In its general form, this problem poses several challenges for Robotics: semantic exploration of unknown environments in search…

机器人学 · 计算机科学 2020-07-31 Ayzaan Wahid , Austin Stone , Kevin Chen , Brian Ichter , Alexander Toshev

Wastewater treatment plants face unique challenges for process control due to their complex dynamics, slow time constants, and stochastic delays in observations and actions. These characteristics make conventional control methods, such as…

This paper develops an efficient multi-agent deep reinforcement learning algorithm for cooperative controls in powergrids. Specifically, we consider the decentralized inverter-based secondary voltage control problem in distributed…

系统与控制 · 电气工程与系统科学 2021-08-03 Dong Chen , Kaian Chen. Zhaojian Li , Tianshu Chu , Rui Yao , Feng Qiu , Kaixiang Lin

We study the adaption of Soft Actor-Critic (SAC), which is considered as a state-of-the-art reinforcement learning (RL) algorithm, from continuous action space to discrete action space. We revisit vanilla discrete SAC and provide an…

机器学习 · 计算机科学 2024-11-21 Haibin Zhou , Tong Wei , Zichuan Lin , junyou li , Junliang Xing , Yuanchun Shi , Li Shen , Chao Yu , Deheng Ye

Reinforcement learning, mathematically described by Markov Decision Problems, may be approached either through dynamic programming or policy search. Actor-critic algorithms combine the merits of both approaches by alternating between steps…

机器学习 · 计算机科学 2023-01-31 Harshat Kumar , Alec Koppel , Alejandro Ribeiro

Although Reinforcement Learning (RL) is effective for sequential decision-making problems under uncertainty, it still fails to thrive in real-world systems where risk or safety is a binding constraint. In this paper, we formulate the RL…

机器学习 · 计算机科学 2022-07-07 Yannis Flet-Berliac , Debabrota Basu

In order to collaborate efficiently with unknown partners in cooperative control settings, adaptation of the partners based on online experience is required. The rather general and widely applicable control setting, where each cooperation…

多智能体系统 · 计算机科学 2019-10-30 Florian Köpf , Samuel Tesfazgi , Michael Flad , Sören Hohmann

Continuous control tasks in reinforcement learning are important because they provide an important framework for learning in high-dimensional state spaces with deceptive rewards, where the agent can easily become trapped into suboptimal…

机器学习 · 计算机科学 2020-07-10 Thang Doan , Bogdan Mazoure , Moloud Abdar , Audrey Durand , Joelle Pineau , R Devon Hjelm

Deep Reinforcement Learning (or just "RL") is gaining popularity for industrial and research applications. However, it still suffers from some key limits slowing down its widespread adoption. Its performance is sensitive to initial…

机器学习 · 计算机科学 2022-08-31 Pierrick Pochelu , Serge G. Petiton , Bruno Conche

The thermal system of battery electric vehicles demands advanced control. Its thermal management needs to effectively control active components across varying operating conditions. While robust control function parametrization is required,…

机器学习 · 计算机科学 2024-08-06 Thomas Rudolf , Philip Muhl , Sören Hohmann , Lutz Eckstein