AISTATS 2021poster33 citations
Robust Imitation Learning from Noisy Demonstrations
Voot Tangkaratt, Nontawat Charoenphakdee, Masashi Sugiyama
Abstract
Robust learning from noisy demonstrations is a practical but highly challenging problem in imitation learning. In this paper, we first theoretically show that robust imitation learning can be achieved by optimizing a classification risk with a symmetric loss. Based on this theoretical finding, we then propose a new imitation learning method that optimizes the classification risk by effectively combining pseudo-labeling with co-training. Unlike existing methods, our method does not require additional labels or strict assumptions about noise distributions. Experimental results on continuous-control benchmarks show that our method is more robust compared to state-of-the-art methods.
BibTeX
@InProceedings{pmlr-v130-tangkaratt21a,
title = { Robust Imitation Learning from Noisy Demonstrations },
author = {Tangkaratt, Voot and Charoenphakdee, Nontawat and Sugiyama, Masashi},
booktitle = {Proceedings of The 24th International Conference on Artificial Intelligence and Statistics},
pages = {298--306},
year = {2021},
editor = {Banerjee, Arindam and Fukumizu, Kenji},
volume = {130},
series = {Proceedings of Machine Learning Research},
month = {13--15 Apr},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v130/tangkaratt21a/tangkaratt21a.pdf},
url = {https://proceedings.mlr.press/v130/tangkaratt21a.html},
abstract = { Robust learning from noisy demonstrations is a practical but highly challenging problem in imitation learning. In this paper, we first theoretically show that robust imitation learning can be achieved by optimizing a classification risk with a symmetric loss. Based on this theoretical finding, we then propose a new imitation learning method that optimizes the classification risk by effectively combining pseudo-labeling with co-training. Unlike existing methods, our method does not require additional labels or strict assumptions about noise distributions. Experimental results on continuous-control benchmarks show that our method is more robust compared to state-of-the-art methods. }
}