Application
Dataset Distillation for Offline Reinforcement Learning
Jonathan Light, Yuanzhe Liu, Ziniu Hu
ICML 2024 Workshop · first public 2024-07-29 · arXiv 2407.20299
In one paragraph
Applies dataset distillation to offline reinforcement learning, distilling a smaller synthetic dataset (DDRL) from offline trajectories so that a policy trained on it matches one trained on the full offline dataset or with percentile behavioral cloning.
Where it sits
- Setting: Other data types
Abstract (verbatim from arXiv)
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 .
BibTeX (generated; prefer the venue's official entry)
@article{light2024dataset,
title = {Dataset Distillation for Offline Reinforcement Learning},
author = {Jonathan Light and Yuanzhe Liu and Ziniu Hu},
journal = {ICML 2024 Workshop},
year = {2024}
}