2 papers
cs.LG2025
Distributional Inverse Reinforcement Learning
Feiyang Wu, Ye Zhao, Anqi Wu
We propose a distributional framework for offline Inverse Reinforcement Learning (IRL) that jointly models uncertainty over reward functions and full distributions of returns. Unli…
cs.RO2025
Structured-Diffuser: Diffusion with Task-Conditioned Structured Priors for Motion Planning
Amelie Minji Kim, Anqi Wu, Junling Mei +1
We propose Structured-Diffuser, a diffusion planner that embeds task and motion structure directly into the noise model. Unlike standard diffusion-based planners that rely on zero-…