Brandon Trabucco, Mariano Phielipp, Glen Berseth
Our paper, Learning Transferable Policies By Inferring Agent Morphology, delivers state-of-the-art generalization and robustness for controlling large collections of reinforcement learning agents with diverse morphologies and designs.
@inproceedings{Trabucco2022AnyMorph,
title={AnyMorph: Learning Transferable Policies By Inferring Agent Morphology},
author={Trabucco Brandon and Phielipp Mariano and Glen Berseth},
journal={International Conference on Machine Learning},
year={2022}
}
All the experiments are done in a Docker container.
To build it, run ./docker_build.sh <device>
, where <device>
can be cpu
or cu101
. It will use CUDA by default.
To build and run the experiments, you need a MuJoCo license. Put it to the root folder before running docker_build.sh
.
./docker_run <device_id> # either GPU id or cpu
cd amorpheus # select the experiment to replicate
bash cwhh.sh # run it on a task
We were using Sacred with a remote MongoDB for experiment management.
For release, we changed Sacred to log to local files instead.
You can change it back to MongDB if you provide credentials in modular-rl/src/main.py
.
- The code is built on top of SMP repository.
- NerveNet Walkers environment are taken and adapted from the original repo.
- Initial implementation of the transformers was taken from the official Pytorch tutorial and modified thereafter.