Human-Drone Collaborative Spatial Crowdsourcing by Memory-Augmented and Distributed Multi-Agent Deep Reinforcement Learning.
Yu WangChi Harold LiuChengzhe PiaoYe YuanRui HanGuoren WangJian TangPublished in: ICDE (2022)
Keyphrases
- multi agent
- reinforcement learning
- cooperative
- multiagent environments
- multi agent systems
- spatio temporal
- collaborative design
- function approximation
- multi agent reinforcement learning
- geographically dispersed
- spatial information
- multi agent coordination
- distributed systems
- state space
- agent interactions
- multiagent systems
- intelligent agents
- multi agent environments
- single agent
- reinforcement learning algorithms
- distributed environment
- collaborative learning
- software agents
- spatial data
- behavioural cloning
- spatial and temporal
- knowledge sharing
- human memory
- markov decision processes
- collaborative decision making
- spatial databases
- team formation
- heterogeneous agents
- mobile agents
- multi agent planning
- multi agent architecture
- autonomous agents
- learning algorithm
- temporal difference