Poster (PDF):
Our approach write up: https://medium.com/@stelmaszczykadam/our-nips-2017-learning-to-run-approach-b80a295d3bb5
Other solutions: https://arxiv.org/abs/1804.00361
Main files:
run_osim.py
to run baselines PPObaselines/baselines/pposgd/pposgd_simple.py
observation processing for PPOexample.py
to run keras-rl DDPG (with old observation processing)es/localhost/launch.py
to run Evolution Strategiesosim-rl/osim/env/run.py#L67
reward hacking
To cite this repository:
@misc{stelmaszczyk2017learning2run,
author = {Stelmaszczyk, Adam and Jarosik, Piotr},
title = "{Our NIPS 2017: Learning to Run source code}",
year = {2017},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/AdamStelmaszczyk/learning2run}},
}