Efficient Rl Via Disentangled Environment And Agent Representations

# Efficient RL via Disentangled Environment and Agent Representations

**arXiv ID:** 2309.02435
**Authors:** Kevin Gmelin, Shikhar Bahl, Russell Mendonca, Deepak Pathak
**Published:** 2023-09-05T17:59:45Z
**Abstract:**
Agents that are aware of the separation between themselves and their environments can leverage this understanding to form effective representations of visual input. We propose an approach for learning such structured representations for RL algorithms, using visual knowledge of the agent, such as its shape or mask, which is often inexpensive to obtain. This is incorporated into the RL objective using a simple auxiliary loss. We show that our method, Structured Environment-Agent Representations, outperforms state-of-the-art model-free approaches over 18 different challenging visual simulation environments spanning 5 different robots. Website at https://sear-rl.github.io/

## Skill Description

This skill is generated from the arXiv paper: Efficient RL via Disentangled Environment and Agent Representations (2309.02435).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2309.02435](http://arxiv.org/abs/2309.02435v1)