Hierarchical automatic curriculum learning: Converting a sparse reward navigation task into dense reward.
Nan JiangSheng JinChangshui ZhangPublished in: Neurocomputing (2019)
Keyphrases
- reinforcement learning
- dictionary learning
- learning algorithm
- learning process
- learning systems
- inverse reinforcement learning
- bandit problems
- online learning
- unsupervised learning
- high dimensional
- partially observable environments
- active learning
- lifelong learning
- technology enhanced
- learning agent
- learning goals
- policy gradient