Sortation Control Using Multi-Agent Deep Reinforcement Learning in N-Grid Sortation System.
Ju-Bong KimHo-bin ChoiGyu-Young HwangKwihoon KimYong-Geun HongYoun-Hee HanPublished in: Sensors (2020)
Keyphrases
- reinforcement learning
- multi agent
- control problems
- optimal control
- control strategies
- control system
- reinforcement learning algorithms
- adaptive control
- control method
- function approximation
- intelligent agents
- action selection
- autonomous agents
- optimal policy
- multi agent systems
- control policy
- single agent
- robot control
- model free
- multiple agents
- control strategy
- multiagent systems
- state space
- heterogeneous agents
- multi agent reinforcement learning
- team formation
- multi agent environments
- grid computing
- function approximators
- temporal difference
- real time
- dynamic programming
- learning algorithm