Automatic Curriculum Learning With Over-repetition Penalty for Dialogue Policy Learning.

Yangyang Zhao Zhenyu Wang 0001 Zhenhua Huang 0002 Automatic Curriculum Learning With Over-repetition Penalty for Dialogue Policy Learning. 14540-14548 2021 AAAI https://doi.org/10.1609/aaai.v35i16.17709 conf/aaai/2021 db/conf/aaai/aaai2021.html#ZhaoWH21