Learning to Navigate in Human Environments via Deep Reinforcement Learning.
Xingyuan GaoShiying SunXiaoguang ZhaoMin TanPublished in: ICONIP (1) (2019)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- language acquisition
- prior knowledge
- learning systems
- learning tasks
- relational reinforcement learning
- human learning
- online learning
- learning problems
- rl algorithms
- deep learning
- temporal difference learning
- autonomous robots
- multi agent reinforcement learning
- state abstraction
- eligibility traces
- learning capabilities
- model free
- learning classifier systems
- unsupervised learning
- knowledge acquisition
- state space
- active learning
- e learning