English

Combating False Negatives in Adversarial Imitation Learning

Machine Learning 2020-02-04 v1 Artificial Intelligence Machine Learning

Abstract

In adversarial imitation learning, a discriminator is trained to differentiate agent episodes from expert demonstrations representing the desired behavior. However, as the trained policy learns to be more successful, the negative examples (the ones produced by the agent) become increasingly similar to expert ones. Despite the fact that the task is successfully accomplished in some of the agent's trajectories, the discriminator is trained to output low values for them. We hypothesize that this inconsistent training signal for the discriminator can impede its learning, and consequently leads to worse overall performance of the agent. We show experimental evidence for this hypothesis and that the 'False Negatives' (i.e. successful agent episodes) significantly hinder adversarial imitation learning, which is the first contribution of this paper. Then, we propose a method to alleviate the impact of false negatives and test it on the BabyAI environment. This method consistently improves sample efficiency over the baselines by at least an order of magnitude.

Keywords

Cite

@article{arxiv.2002.00412,
  title  = {Combating False Negatives in Adversarial Imitation Learning},
  author = {Konrad Zolna and Chitwan Saharia and Leonard Boussioux and David Yu-Tung Hui and Maxime Chevalier-Boisvert and Dzmitry Bahdanau and Yoshua Bengio},
  journal= {arXiv preprint arXiv:2002.00412},
  year   = {2020}
}

Comments

This is an extended version of the student abstract published at 34th AAAI Conference on Artificial Intelligence

R2 v1 2026-06-23T13:28:12.891Z