Self-Adaptive Imitation Learning: Learning Tasks with Delayed Rewards from Sub-optimal Demonstrations.
Zhuangdi ZhuKaixiang LinBo DaiJiayu ZhouPublished in: AAAI (2022)
Keyphrases
- learning tasks
- imitation learning
- reinforcement learning
- transfer learning
- machine learning
- learning algorithm
- supervised learning
- learning problems
- multi task
- machine learning algorithms
- function approximation
- learning experience
- multi label
- learning models
- markov decision processes
- dynamic programming
- labeled data
- information extraction
- maximum margin
- high dimensional