Trpo

    #john schulman

    #john schulman openai

    #policy gradient vs q learning

    #reinforcement learning to optimize computation of machine learning

    #jonathan schulman

    #wgan

    #infogan

    #trpo

    #trust region policy optimization

    #deepstack

    #policy gradient

    #deep learning freeze layer

    #keras pretrained overfitting

    #keras fine tuning

    #holly grimm

    #blackjack reinforcement learning

    #reinforcement learning bootcamp

    #deep rl bootcamp 2018

    #reinforcement learning syllabus