A Cascaded Supervised Learning Approach to Inverse Reinforcement Learning.
Edouard KleinBilal PiotMatthieu GeistOlivier PietquinPublished in: ECML/PKDD (1) (2013)
Keyphrases
- inverse reinforcement learning
- supervised learning
- bayesian nonparametric
- partially observable environments
- temporal difference
- preference elicitation
- unsupervised learning
- reinforcement learning
- reward function
- learning tasks
- training data
- training set
- active learning
- learning algorithm
- machine learning
- semi supervised
- pairwise
- hidden markov models