Corpus ID: 59536625

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

@inproceedings{ChevalierBoisvert2019BabyAIAP,
  title={BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning},
  author={Maxime Chevalier-Boisvert and Dzmitry Bahdanau and Salem Lahlou and Lucas Willems and Chitwan Saharia and Thien Huu Nguyen and Yoshua Bengio},
  booktitle={ICLR},
  year={2019}
}
  • Maxime Chevalier-Boisvert, Dzmitry Bahdanau, +4 authors Yoshua Bengio
  • Published in ICLR 2019
  • Computer Science
  • 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. [...] Key Method The platform also provides a heuristic expert agent for the purpose of simulating a human teacher. We report baseline results and estimate the amount of human involvement that would be required to train a neural network-based…Expand Abstract

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 16 CITATIONS

    BabyAI++: Towards Grounded-Language Learning beyond Memorization

    VIEW 5 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Combating False Negatives in Adversarial Imitation Learning

    VIEW 4 EXCERPTS
    CITES METHODS & RESULTS

    Mastering emergent language: learning to guide in simulated navigation

    VIEW 4 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED