Digital Human Interactive Recommendation Decision-Making Based on Reinforcement Learning

no code implementations • 6 Oct 2022 • Xiong Junwu, Xiaoyun Feng, Yunzhou Shi, James Zhang, Zhongzhou Zhao, Wei Zhou

Our proposed framework learns through real-time interactions between the digital human and customers dynamically through the state-of-art RL algorithms, combined with multimodal embedding and graph embedding, to improve the accuracy of personalization and thus enable the digital human agent to timely catch the attention of the customer.

Decision Making Graph Embedding +2

Hindsight Curriculum Generation Based Multi-Goal Experience Replay

no code implementations • 1 Jan 2021 • Xiaoyun Feng

Based on the hindsight strategy, we introduce a novel multi-goal experience replay method that automatically generates a training curriculum, namely Hindsight Curriculum Generation (HCG).

Reinforcement Learning (RL)