Generalized Inverse Planning: Learning Lifted non-Markovian Utility for Generalizable Task Representation.
Sirui XieFeng GaoSong-Chun ZhuPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- learning process
- online learning
- prior knowledge
- learning algorithm
- unsupervised learning
- predictive state representations
- stochastic domains
- visual representation
- learning systems
- supervised learning
- background knowledge
- mobile learning
- domain independent
- dynamic programming
- active learning
- reinforcement learning agents
- bayesian networks