Search Results for author: Salem Lahlou

Found 4 papers, 3 papers with code

GFlowNet Foundations

no code implementations17 Nov 2021 Yoshua Bengio, Tristan Deleu, Edward J. Hu, Salem Lahlou, Mo Tiwari, Emmanuel Bengio

Generative Flow Networks (GFlowNets) have been introduced as a method to sample a diverse set of candidates in an active learning context, with a training objective that makes them approximately sample in proportion to a given reward function.

Active Learning

DEUP: Direct Epistemic Uncertainty Prediction

2 code implementations16 Feb 2021 Moksh Jain, Salem Lahlou, Hadi Nekoei, Victor Butoi, Paul Bertin, Jarrid Rector-Brooks, Maksym Korablyov, Yoshua Bengio

Epistemic uncertainty is the part of out-of-sample prediction error due to the lack of knowledge of the learner.

Active Learning

Mastering Rate based Curriculum Learning

1 code implementation14 Aug 2020 Lucas Willems, Salem Lahlou, Yoshua Bengio

Recent automatic curriculum learning algorithms, and in particular Teacher-Student algorithms, rely on the notion of learning progress, making the assumption that the good next tasks are the ones on which the learner is making the fastest progress or digress.

BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning

4 code implementations ICLR 2019 Maxime Chevalier-Boisvert, Dzmitry Bahdanau, Salem Lahlou, Lucas Willems, Chitwan Saharia, Thien Huu Nguyen, Yoshua Bengio

Allowing humans to interactively train artificial agents to understand language instructions is desirable for both practical and scientific reasons, but given the poor data efficiency of the current learning methods, this goal may require substantial research efforts.

Grounded language learning

Cannot find the paper you are looking for? You can Submit a new open access paper.