Learning More Complex Actions with Deep Reinforcement Learning.
Chenxi WangYoutian DuShengyuan XieYongdi LuPublished in: IRC (2021)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- online learning
- learned knowledge
- temporal difference learning
- learning problems
- supervised learning
- learning systems
- active learning
- prior knowledge
- state space
- goal directed
- deep learning
- autonomous learning
- previously learned
- action models
- learning agents
- action sequences
- robot control
- learning capabilities
- action selection
- decision theoretic
- learning tasks
- unsupervised learning