Jiafei Lyu

Model-based Offline RL via Robust Value-Aware Model Learning with Implicitly Differentiable Adaptive Weighting

Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts

Cross-domain Offline Policy Adaptation with Dynamics- and Value-aligned Data Filtering

Cross-Domain Offline Policy Adaptation via Selective Transition Correction

PROF: An LLM-based Reward Code Preference Optimization Framework for Offline Imitation Learning

Temporal Difference Learning with Constrained Initial Representations

EgoPlan: Towards Effective Embodied Agents via Egocentric Planning

Cross-Domain Offline Policy Adaptation with Optimal Transport and Dataset Constraint

ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning

VLP: Vision-Language Preference Learning for Embodied Manipulation

Offline-to-Online Reinforcement Learning with Prioritized Experience Selection

Egocentric Vision Language Planning