Shengyi Jiang

Invariant Action Effect Model for Reinforcement Learning

2022 · Proceedings of the AAAI Conference on Artificial Intelligence

Good representations can help RL agents perform concise modeling of their surroundings, and thus support effective decision-making in complex environments. Previous methods learn good representations by imposing extra constraints on dynamics. However, in the causal …

A New Evaluation Method: Evaluation Data and Metrics for Chinese Grammatical Error Correction

2022 · Research Square

Abstract As a fundamental task in natural language processing (NLP), Chinese Grammatical Error Correction (CGEC) [1–3] has gradually received widespread attention and become a research hotspot. However, one obvious deficiency of the existing CGEC evaluation …