Search Constraints

Start Over
Filtering by: Creator Greer, Adam T. Remove constraint Creator: Greer, Adam T. Committee Member Tadepalli, Prasad Remove constraint Committee Member: Tadepalli, Prasad Contributor Fern, Alan P. Remove constraint Contributor: Fern, Alan P.

Search Results

  • Re-understanding Finite-State Representations of Recurrent Policy Networks

    Creator:
    Danesh, Mohamad H.
    Abstract:
    We propose an approach for understanding control policies represented as recurrent neural networks. Recent work has approached this problem by transforming such recurrent policy networks into finite-state machines (FSM) and then analyzing the equivalent minimized FSM. While this led to interesting insights, the minimization process can obscure a deeper understanding...
    Resource Type:
    Masters Thesis
    Full Text:
    agent. For instance, [17] ex- plains policy outputs by visualizations and t-SNE embeddings, [24