Despite extreme sample inefficiency, on-policy reinforcement learning, aka policy gradients, has become a fundamental tool in decision-making problems. With the recent advances in GPU-driven simulation, the ability to collect large amounts of data for RL training has scaled exponentially. However, we show that current RL methods, e.g. PPO, fail to ingest the benefit of parallelized environments beyond a certain point and their performance saturates. To address this, we propose a new on-policy RL algorithm that can effectively leverage large-scale environments by splitting them into chunks and fusing them back together via importance sampling. Our algorithm, termed SAPG, shows significantly higher performance across a variety of challenging environments where vanilla PPO and other strong baselines fail to achieve high performance. Our code will be open-sourced upon acceptance.
Allegro Kuka Regrasping
Allegro Kuka Reorientation
PCA based analysis
MLP reconstruction based analysis
@inproceedings{sapg2024,
title = {SAPG: Split and Aggregate Policy Gradients},
author = {Singla, Jayesh and Agarwal, Ananye and Pathak, Deepak},
booktitle = {Proceedings of the 41st International Conference on Machine Learning (ICML 2024)},
year = {2024},
series = {Proceedings of Machine Learning Research},
address = {Vienna, Austria},
month = {July},
publisher = {PMLR},
}