Adversarial Batch Inverse Reinforcement Learning: Learn to Reward from Imperfect Demonstration for Interactive Recommendation

no code implementations • 30 Oct 2023 • Jialin Liu, Xinyan Su, Zeyu He, Xiangyu Zhao, Jun Li

In this research, we focus on the problem of learning to reward (LTR), which is fundamental to reinforcement learning.

Recommendation Systems reinforcement-learning

A General Neural Causal Model for Interactive Recommendation

no code implementations • 30 Oct 2023 • Jialin Liu, Xinyan Su, Peng Zhou, Xiangyu Zhao, Jun Li

Mitigation of the survivor bias is achieved though counterfactual consistency.

counterfactual Counterfactual Inference +1

Influence Maximization with Unknown Individual Effect on General Network

no code implementations • 28 Jan 2023 • Xinyan Su, Zhiheng Zhang, Jiyan Qiu, Jun Li

The identification of a seed set to maximize information spread in a network is crucial, a concept known as Influence Maximization (IM).

Causal Inference