Learning Task-Distribution Reward Shaping with Meta-Learning.

Haosheng Zou Tongzheng Ren Dong Yan Hang Su Jun Zhu

Published in: AAAI (2021)

Keyphrases

meta learning
learning tasks
inductive learning
learning algorithm
decision trees
training data
multi agent
active learning
classification accuracy
knowledge representation
software engineering
model selection
background knowledge
reward shaping