Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation.
Juncheng LiXin WangSiliang TangHaizhou ShiFei WuYueting ZhuangWilliam Yang WangPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- supervised learning
- unsupervised learning
- function approximation
- state space
- model free
- navigation systems
- robotic control
- semi supervised
- unsupervised manner
- markov decision processes
- machine learning
- action selection
- active learning
- learning algorithm
- neural network
- intelligent systems
- meta reasoning
- policy search
- website
- autonomous vehicles
- obstacle avoidance
- temporal difference
- multi agent
- information space
- robot navigation
- information technology
- learning classifier systems
- optimal control
- learning process
- learning problems