Towards Interpretable Deep Reinforcement Learning Models via Inverse Reinforcement Learning.
Yuansheng XieSoroush VosoughiSaeed HassanpourPublished in: ICPR (2022)
Keyphrases
- learning models
- inverse reinforcement learning
- reinforcement learning
- reward function
- preference elicitation
- learning algorithm
- machine learning
- semi supervised learning
- learning problems
- learning tasks
- loss function
- machine learning algorithms
- temporal difference
- conditional random fields
- classification models
- support vector
- transfer learning
- kernel methods
- learning process
- function approximation
- high dimensional
- image segmentation
- active learning