Inducing Cooperation via Team Regret Minimization based Multi-Agent Deep Reinforcement Learning.
Runsheng YuZhenyu ShiXinrun WangRundong WangBuhong LiuXinwen HouHanjiang LaiBo AnPublished in: CoRR (2019)
Keyphrases
- multi agent
- regret minimization
- reinforcement learning
- agent cooperation
- multi agent learning
- heterogeneous agents
- robocup soccer
- cooperative agents
- team formation
- cooperating agents
- cooperative
- multi agent systems
- game theoretic
- nash equilibrium
- multi agent environments
- multi agent reinforcement learning
- intelligent agents
- model free
- multiagent systems
- single agent
- function approximation
- team members
- autonomous agents
- robocup rescue
- state space
- game theory
- markov decision processes
- reinforcement learning algorithms
- software agents
- coalition formation
- robotic soccer
- learning agents
- temporal difference
- supervised learning
- multiple agents
- win win
- machine learning
- learning algorithm