TY - JOUR
T1 - Optimization for Reinforcement Learning
T2 - From a single agent to cooperative agents
AU - Lee, Donghwan
AU - He, Niao
AU - Kamalaruban, Parameswaran
AU - Cevher, Volkan
N1 - Publisher Copyright:
© 1991-2012 IEEE.
PY - 2020/5
Y1 - 2020/5
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85084554989&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85084554989&partnerID=8YFLogxK
U2 - 10.1109/MSP.2020.2976000
DO - 10.1109/MSP.2020.2976000
M3 - Article
AN - SCOPUS:85084554989
SN - 1053-5888
VL - 37
SP - 123
EP - 135
JO - IEEE Signal Processing Magazine
JF - IEEE Signal Processing Magazine
IS - 3
M1 - 9084325
ER -