# LG AI Research — [NeurIPS 2022] LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation

- Company: LG AI Research (lgresearch.ai)
- Announced: 2023-01-06
- Category: research-paper
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://www.lgresearch.ai/blog/view?seq=294
- Record: https://forck.live/items/4911-neurips-2022-lobsdice-offline-learning-from-observation-via-stationary
- Subject: EXAONE

LG AI Research introduces LobsDICE, a new offline learning from observation algorithm accepted at NeurIPS 2022, which uses stationary distribution correction estimation to mimic expert policy from state-only demonstrations without environment interaction.

## Evidence

Verbatim from https://www.lgresearch.ai/blog/view?seq=294:

> This paper focuses on the fact that humans learn by observing state-only expert demonstrations and proposes a learning from observation (LfO) method in an offline setting.

---

Record: https://forck.live/items/4911-neurips-2022-lobsdice-offline-learning-from-observation-via-stationary
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md