Time-sequence Action-Decision and Navigation Through Stage Deep Reinforcement Learning in Complex Dynamic Environments.
Huimu WangZhiqiang PuJianqiang YiTenghai QiuZhen LiuZhaoyang LiuPublished in: SSCI (2019)
Keyphrases
- dynamic environments
- reinforcement learning
- potential field
- autonomous navigation
- changing environment
- mobile robot
- reinforcement learning agents
- autonomous agents
- agent systems
- path planning
- decision making
- collision avoidance
- single agent
- reinforcement learning algorithms
- reward shaping
- autonomous systems
- highly dynamic environments
- plan execution
- learning algorithm
- adaptive control
- collision free
- belief space
- action selection
- indoor environments
- software agents
- state space
- multi agent systems
- partially observable domains