GALOPP: Multi-Agent Deep Reinforcement Learning For Persistent Monitoring With Localization Constraints.
Manav MishraPrithvi PoddarJingxi ChenPratap TokekarP. B. SujitPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- multi agent
- function approximation
- cooperative
- multi agent systems
- real time
- monitoring system
- state space
- multi agent reinforcement learning
- multiagent systems
- intelligent agents
- dynamic programming
- learning agents
- single agent
- model free
- deep learning
- optic disc
- constraint programming
- agent oriented
- partially observable
- action selection
- multiple agents
- coalition formation
- optimal control
- constraint satisfaction
- optimal policy
- learning process
- machine learning