English

Automated curriculum generation for Policy Gradients from Demonstrations

Machine Learning 2019-12-03 v1 Artificial Intelligence Machine Learning

Abstract

In this paper, we present a technique that improves the process of training an agent (using RL) for instruction following. We develop a training curriculum that uses a nominal number of expert demonstrations and trains the agent in a manner that draws parallels from one of the ways in which humans learn to perform complex tasks, i.e by starting from the goal and working backwards. We test our method on the BabyAI platform and show an improvement in sample efficiency for some of its tasks compared to a PPO (proximal policy optimization) baseline.

Keywords

Cite

@article{arxiv.1912.00444,
  title  = {Automated curriculum generation for Policy Gradients from Demonstrations},
  author = {Anirudh Srinivasan and Dzmitry Bahdanau and Maxime Chevalier-Boisvert and Yoshua Bengio},
  journal= {arXiv preprint arXiv:1912.00444},
  year   = {2019}
}

Comments

Accepted to Deep RL Workshop at NeurIPS 2019

R2 v1 2026-06-23T12:32:24.243Z