Multi-Agent Collaborative Exploration through Graph-based Deep Reinforcement Learning.
Tianze LuoBudhitama SubagdjaDi WangAh-Hwee TanPublished in: ICA (2019)
Keyphrases
- reinforcement learning
- multi agent
- exploration strategy
- action selection
- exploration exploitation
- active exploration
- cooperative
- function approximation
- single agent
- multi agent environments
- learning algorithm
- collaborative learning
- semi supervised
- multi user
- multi agent reinforcement learning
- intelligent agents
- markov decision processes
- reinforcement learning agents
- traffic signal control
- model based reinforcement learning
- multi agent systems
- exploratory search
- reinforcement learning algorithms
- multiple agents
- temporal difference
- knowledge sharing
- state space
- collaborative environment
- geographically dispersed
- graph model
- learning problems
- supervised learning
- multiagent environments
- neural network
- heterogeneous agents
- multi agent coordination
- dynamic programming
- learning process