Firm-level behavior control after large-scale urban flooding using multi-agent deep reinforcement learning.
Shaofeng YangYoshiki OgawaKoji IkeuchiYuki AkiyamaRyosuke ShibasakiPublished in: GeoSim@SIGSPATIAL (2019)
Keyphrases
- reinforcement learning
- multi agent
- control problems
- robot behavior
- multi agent environments
- optimal control
- control strategies
- robot control
- information technology
- machine learning
- control system
- control policy
- reinforcement learning algorithms
- action selection
- model free
- small scale
- function approximation
- state space
- cooperative
- learning algorithm
- learning agents
- agent based models
- urban planning
- neural network
- robotic control
- temporal difference
- adaptive control
- autonomous robots
- optimal policy
- real robot
- urban areas
- control method
- agent behavior
- markov decision processes
- multiagent systems
- multi agent systems