Offline reinforcement learning often requires a quality dataset that we can train a policy on. However, in many situations, it is not possible to get such a dataset, nor is it easy to train a policy to perform well in the actual environment given the offline data. We propose using data distillation to train and distill a better dataset which can then be used for training a better policy model. We show that our method is able to synthesize a dataset where a model trained on it achieves similar performance to a model trained on the full dataset or a model trained using percentile behavioral cloning. Our project site is available at https://datasetdistillation4rl.github.io . We also provide our implementation at https://github.com/ggflow123/DDRL .
@article{arxiv.2407.20299,
title = {Dataset Distillation for Offline Reinforcement Learning},
author = {Jonathan Light and Yuanzhe Liu and Ziniu Hu},
journal= {arXiv preprint arXiv:2407.20299},
year = {2025}
}
Comments
ICML 2024 DMLR Workshop Our project site is available at https://datasetdistillation4rl.github.io We also provide our implementation at https://github.com/ggflow123/DDRL