Shenghong He — accepted AI-conference papers

2026

Reliability-Guaranteed and Reward-Seeking Sequence Modeling for Model-Based Offline Reinforcement Learning

Shenghong He, Chao Yu, Qian Lin, Yile Liang, Donghui Li, Xuetao Ding

AAAI 2026technical

As a data-driven learning approach, model-based offline reinforcement learning (MORL) aims to learn a policy by exploiting a dynamics model derived from an existing dataset. Applying conservative quantification to the dynamics model, most existing works on MORL generate trajectories that approximate

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Conservative Offline Goal-Conditioned Implicit V-Learning

Kaiqiang Ke, Qian Lin, Zongkai Liu, Shenghong He, Chao Yu

ICML 2025poster

Offline goal-conditioned reinforcement learning (GCRL) learns a goal-conditioned value function to train policies for diverse goals with pre-collected datasets. Hindsight experience replay addresses the issue of sparse rewards by treating intermediate states as goals but fails to complete goal-stitc…

Cited by 0 Source ↗PDF ↗Scholar ↗