Papers › Automated curriculum generation for Policy Gradients from Demonstrations

Automated curriculum generation for Policy Gradients from Demonstrations

1 Dec 2019arXiv:1912.00444archive 2025-07-28

Anirudh Srinivasan, Dzmitry Bahdanau, Maxime Chevalier-Boisvert, Yoshua Bengio

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.

PaperPDFCode

Code

Genius1237/babyai officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Instruction Following

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Entropy RegularizationPPOTest

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections