Addressing the Task of Rocket Recycling with Deep Reinforcement Learning.
Guangyin JinJincai HuangYang-He FengGuangquan ChengZhong LiuQi WangPublished in: ICIT (2018)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- learning algorithm
- state space
- markov decision processes
- optimal policy
- learning process
- temporal difference learning
- model free
- reinforcement learning methods
- multi agent reinforcement learning
- action space
- control problems
- robotic control
- temporal difference
- optimal control
- databases
- multi agent systems
- genetic algorithm
- machine learning
- supervised learning
- artificial neural networks
- search algorithm
- learning capabilities
- support vector
- multi agent
- multiscale
- knowledge base
- autonomous learning
- policy search