Papers by David Speck

    1 papers
    Learning to request guidance in emergent language (D19-64)

    Copied to clipboard

    Challenge: Previous research into agent communication has shown that a pre-trained guide can speed up the learning process of an imitation learning agent.
    Approach: They extend one-directional communication by a one-bit communication channel from the learner back to the guide and limit the guidance by penalizing the learners for these requests.
    Outcome: The proposed guide can speed up the learning process of an imitation learning agent by providing the learner with discrete messages in an emerged language about how to solve the task.

    What is GenGO?

    GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

    Information

    About
    Limitations