New Template for Experimentation on Adversarial Motion Priors (AMP) Algorithm via DeepMimic Library

[Shivamkak19]

This template provides a new AI Scientist template for experimentation on Adversarial Motion Priors (AMP) algorithm via the DeepMimic library

Adversarial Motion Priors (Peng et al., 2021) presents an unsupervised reinforcement learning approach to character animation based on learning from unstructured motion data to cast natural behaviors on simulated characters.

Paper Website available here:

https://xbpeng.github.io/projects/AMP/index.html

The paper was released with the DeepMimic library as a framework for training AMP agents. This template for the AI-Scientist allows users to experiment with modifications to the base AMP algorithm within the DeepMimic library.

DeepMimic requires a somewhat complicated build process, so I wrote a bash script DeepMimic/auto_setup.sh that handles the entire setup process.

The experiment.py file implements a simple training run on an AMP agent for 3 different motion files:

"DeepMimic/data/motions/humanoid3d_walk.txt"
"DeepMimic/data/motions/humanoid3d_jog.txt"
"DeepMimic/data/motions/humanoid3d_run.txt"

Anothe popular (and more recent) option for experimenting with AMP is through the ProtoMotions Library, which uses NVIDIA's IsaacGym as a backbone. For this reason, I decided to go with DeepMimic as a more light-weight alternative that still allows users to test and evaluate experimental conditions on the base AMP algorithm.

Please follow templates/amp/README.md for specific setup instructions, and please see templates/amp/examples/ for example paper generations. Note, that the Semantic Scholar API was not used for any of these generations, as I am on the waiting list for an API key.

I generated these papers on a "fresh-out-the-box" A100 (40 GB SXM4) on Lambda Labs by followings the instructions as indicated in templates/amp/README.md.

Hope we can all learn something cool using this template! Definitely ping me if you are able to generate an awesome paper with it.

[Shivamkak19]

@conglu1997 Hi! Wanted to bump this

[Shivamkak19]

@conglu1997 @corochann Following up here to publish the template!

[conglu1997]

Thanks so much - please see the reviews, would it be possible to move the marked stuff external to avoid including big files into the repo?

[conglu1997]

Would it be possible to move this stuff to the README and not include submodules?

[conglu1997]

Could you move examples to an external github folder?