Hierarchical Deep Reinforcement Learning for Multi-robot Cooperation in Partially Observable Environment.
Zhixuan LiangJiannong CaoWanyu LinJinlin ChenHuafeng XuPublished in: CogMI (2021)
Keyphrases
- initially unknown
- partially observable
- multi robot
- reinforcement learning
- mobile robot
- real robot
- state space
- markov decision processes
- reward function
- partial observability
- path planning
- decision problems
- multiple robots
- dynamical systems
- partially observable markov decision process
- partially observable domains
- partially observable environments
- uncertain environments
- robotic systems
- markov decision problems
- multi robot systems
- robot navigation
- multi agent
- multi robot exploration
- function approximation
- optimal policy
- dynamic environments
- robot teams
- infinite horizon
- model free
- autonomous robots
- belief state
- dynamic programming
- motion planning
- multi agent systems
- learning algorithm
- reinforcement learning algorithms
- machine learning
- surveillance system
- orders of magnitude
- special case