Optimization for Reinforcement Learning: From a single agent to cooperative agents
Optimization for Reinforcement Learning: From a single agent to cooperative agents
复制标题
DOI：
10.1109/msp.2020.2976000
复制
发表时间：
2019-12
影响因子：
14.9
通讯作者：
Dong-hwan Lee;Niao He;Parameswaran Kamalaruban;V. Cevher
中科院分区：
文献类型：
--
作者：
Dong-hwan Lee;Niao He;Parameswaran Kamalaruban;V. Cevher
在深度神经网络最新进展的推动下，强化学习（RL）已经成为人们关注的焦点，因为人工智能最近取得了许多突破，包括在游戏中击败人类（例如国际象棋、围棋、星际争霸）、自动驾驶汽车、智能家居自动化和服务机器人等。尽管取得了这些显著的成就，但单个RL代理仍然无法完成许多基本任务。这样的例子比比皆是，从多人游戏、多机器人、蜂窝天线倾斜控制、交通控制系统、智能电网到网络管理。
Fueled by recent advances in deep neural networks, reinforcement learning (RL) has been in the limelight because of many recent breakthroughs in artificial intelligence, including defeating humans in games (e.g., chess, Go, StarCraft), self-driving cars, smart-home automation, and service robots, among many others. Despite these remarkable achievements, many basic tasks can still elude a single RL agent. Examples abound, from multiplayer games, multirobots, cellular-antenna tilt control, traffic-control systems, and smart power grids to network management.