Skip to content

[IJCAI'24] An index of algorithms, approaches, and systems on cross-domain policy transfer for embodied agents

Notifications You must be signed in to change notification settings

t6-thu/awesome-cross-domain-policy-transfer-for-embodied-agents

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

52 Commits
 
 

Repository files navigation

awesome-cross-domain-policy-transfer-for-embodied-agents Awesome

This is a collection of research and review papers for cross-domain policy transfer for embodied agents. Feel free to star and fork. Original paper: A Comprehensive Survey of Cross-Domain Policy Transfer for Embodied Agents, IJCAI 2024.

Maintainers

Haoyi Niu, Jianming Hu, Guyue Zhou, Xianyuan Zhan. (Tsinghua University)

Architecture of the survey

The main architecture of the survey: domain gap taxonomy, overarching insights on methodologies, and future trends. main

Approaches categorized by handling different domain gaps

Cross-Appearance Policy Transfer

Appearance gaps arise when observations in the source domain (e.g., simulations) exhibit differences in colors, background objects, illumination conditions, and rendering textures as compared to the target domain (e.g., reality), such as variations in coarse and fine rendering or high and low resolutions.

Cross-Viewpoint Policy Transfer

Viewpoint gaps arise when the configuration of sensor setups (e.g., camera position and angles, etc.) can significantly influence the downstream policy learning of embodied agents.

Cross-Dynamics Policy Transfer

Dynamics gaps occur when interactions between embodiments and their deploying environments, or interactions among different parts of the embodiment itself, follow different transitional dynamics, such as stiffness, gear dead zones of embodiments, body mass, and friction.

Cross-Morphology Policy Transfer

Morphology gaps arise when target embodiments exhibit different morphological designs compared to the source domain agents, e.g., variations in joint types, module shapes, and lengths, which may ultimately lead to a dynamics mismatch. Morphology gaps may also encompass variations in the dimensions and semantic meanings of state and action spaces, such as the number of observational sensors, limbs, and end effectors.

Cross-Modality Policy Transfer

Cross-Multi-Gap Policy Transfer

In many complex tasks, we might simultaneously encounter multiple types of domain gaps due to substantially different embodiments and deployed environments.

Existing Benchmarks

Progress: Updated CoRL 2024!

Citations

If the insights, categorizations, analyses and encapsulations in this survey paper/github collection are helpful with your project development, please cite the following paper:

@inproceedings{
    niu2024comprehensive,
    title={A Comprehensive Survey of Cross-Domain Policy Transfer for Embodied Agents},
    author={Niu, Haoyi and Hu, Jianming and Zhou, Guyue and Zhan, Xianyuan},
    booktitle={International Joint Conference on Artificial Intelligence},
    year={2024}
}

About

[IJCAI'24] An index of algorithms, approaches, and systems on cross-domain policy transfer for embodied agents

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published