Multi-robot Cooperation Strategy in a Partially Observable Markov Game Using Enhanced Deep Deterministic Policy Gradient.
Qirong TangJingtao ZhangFangchao YuPengjie XuZhongqun ZhangPublished in: ICSI (2) (2019)
Keyphrases
- multi robot
- coalitional game theory
- policy gradient
- initially unknown
- mobile robot
- path planning
- partially observable markov
- cooperative
- game theory
- average reward
- multi agent systems
- reinforcement learning
- single agent
- function approximation
- robotic systems
- multi agent
- markov decision processes
- multi robot coordination
- bayesian networks