# LG AI Research — [ICLR 2022] Deep Reinforcement Learning Technologies for Effective Single General-Purpose Policy

- Company: LG AI Research (lgresearch.ai)
- Announced: 2022-04-28
- Category: research-paper
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://www.lgresearch.ai/blog/view?seq=207
- Record: https://forck.live/items/4952-iclr-2022-deep-reinforcement-learning-technologies-for-effective-single
- Subject: EXAONE

Sunghoon Hong, a researcher at LG AI Research, and his work on a single general-purpose policy for multi-task reinforcement learning using graph neural networks and transformers, which was published at ICLR 2022.

## Evidence

Verbatim from https://www.lgresearch.ai/blog/view?seq=207:

> This paper deals with the single general-purpose policy for the study goal of training human- or animal-shaped robots composed of multiple joints to move forward by controlling the torque of each joint (Figure 2). [1]

---

Record: https://forck.live/items/4952-iclr-2022-deep-reinforcement-learning-technologies-for-effective-single
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md