MetaMorph: Learning Universal Controllers with Transformers
This is the code for the paper
MetaMorph: Learning Universal Controllers with Transformers
Agrim Gupta, Linxi Fan, Surya Ganguli, Fei-Fei Li
Multiple domains like vision, natural language, and audio are witnessing tremendous progress by leveraging Transformers for large scale pre-training followed by task specific fine tuning. In contrast, in robotics we primarily train a single robot for a single task. However, modular robot systems now allow for the flexible combination of general-purpose building blocks into task optimized morphologies. However, given the exponentially large number of possible robot morphologies, training a controller for each new design is impractical. In this work, we propose MetaMorph, a Transformer based approach to learn a universal controller over a modular robot design space. MetaMorph is based on the insight that robot morphology is just another modality on which we can condition the output of a Transformer. Through extensive experiments we demonstrate that large scale pre-training on a variety of robot morphologies results in policies with combinatorial generalization capabilities, including zero shot generalization to unseen robot morphologies. We further demonstrate that our pre-trained policy can be used for sample-efficient transfer to completely new robot morphologies and tasks.
Code Structure
The code consists of two main components:
- Metamorph: Code for joint pre-training of different robots.
- Environments and evaluation tasks: Three pre-training environments and two evaluation environments.
Benchmark
We also provide Unimal-100 benchmark. The benchmark consists of 100 train morphologies, 1600 morphologies with dynamics variations, 800 morphologies with kinematics variations, and 100 test morphologies.
# Install gdown
pip install gdown
# Download data
gdown 1LyKYTCevnqWrDle1LTBMlBF58RmCjSzM
# Unzip
unzip unimals_100.zip
Setup
We provide Dockerfile for easy installation and development. If you prefer to work without docker please take a look at Dockerfile and ensure that your local system has all the necessary dependencies installed.
Training
# Build docker container. Ensure that MuJoCo license is present: docker/mjkey.txt
./scripts/build_docker.sh
# Joint pre-training. Please change MOUNT_DIR location inside run_docker_gpu.sh
# Finally ensure that ENV.WALKER_DIR points to benchmark files and is accessible
# from docker.
./scripts/run_docker_gpu.sh python tools/train_ppo.py --cfg ./configs/ft.yaml
The default parameters assume that you are running the code on a machine with atlesat 1 GPU.
Citation
If you find this code useful, please consider citing:
@inproceedings{
gupta2022metamorph,
title={MetaMorph: Learning Universal Controllers with Transformers},
author={Agrim Gupta and Linxi Fan and Surya Ganguli and Li Fei-Fei},
booktitle={International Conference on Learning Representations},
year={2022},
url={https://openreview.net/forum?id=Opmqtk_GvYL}
}
Credit
This codebase would not have been possible without the following amazing open source codebases:
![[ICLR 2022] DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://github.com/IDEA-opensource/DAB-DETR/raw/main/figure/arch_new2.png)
336 Dec 25, 2022
87 Jan 8, 2023
37 Nov 27, 2022
274 Jan 5, 2023
366 Dec 28, 2022
22 Sep 8, 2022
174 Dec 29, 2022
50 Oct 28, 2022
55 Dec 21, 2022
3 Aug 20, 2022
31 Nov 22, 2022
221 Dec 31, 2022
22 Sep 15, 2022
29 Nov 29, 2022
34 Oct 26, 2022
76 Dec 13, 2022
155 Dec 26, 2022
83 May 11, 2022