Nicolas Espinosa-Dice — accepted AI-conference papers

2025

Efficient Imitation under Misspecification

Nicolas Espinosa-Dice, Sanjiban Choudhury, Wen Sun, Gokul Swamy

ICLR 2025poster

We consider the problem of imitation learning under misspecification: settings where the learner is fundamentally unable to replicate expert behavior everywhere. This is often true in practice due to differences in observation space and action space expressiveness (e.g. perceptual or morphological d…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Scaling Offline RL via Efficient and Expressive Shortcut Models

Nicolas Espinosa-Dice, Yiyi Zhang, Yiding Chen, Bradley Guo, Owen Oertell, Gokul Swamy +2

NeurIPS 2025poster

Diffusion and flow models have emerged as powerful generative approaches capable of modeling diverse and multimodal behavior. However, applying these models to offline RL remains challenging due to the iterative nature of their noise sampling processes, making policy optimization difficult. In this…

Cited by 0 Source ↗Scholar ↗