https://andrew-silva.github.io/tags/neural-networks/ Recent content in neural networks on Andrew Silva Hugo -- gohugo.io en Mon, 21 Dec 2020 03:58:16 +0000 https://andrew-silva.github.io/posts/learning-differentiable-decision-trees-for-reinforcement-learning/ Mon, 21 Dec 2020 03:58:16 +0000 https://andrew-silva.github.io/posts/learning-differentiable-decision-trees-for-reinforcement-learning/ In conjunction with an earlier post on the use of Differentiable Decision Trees (DDTs) for interpretable reinforcement learning, this post will cover my recent AISTATS paper Optimization Methods for Interpretable Differentiable Decision Trees in Reinforcement Learning. In my earlier post, I laid out some reasons that we might want to use DDTs for reinforcement learning: they afford discretization for interpretable plans, they allow for warm-starting and human initialization, and they are surprisingly robust to hyperparameter selection (things like learning rates, number of layers, and so on). https://andrew-silva.github.io/posts/interpretable-machine-learning/ Tue, 10 Mar 2020 20:35:58 +0000 https://andrew-silva.github.io/posts/interpretable-machine-learning/ A brief foreword: This entire post is a high-level summary of the motivations and contributions of my paper which was recently accepted to AISTATS 2020! For some math on why Q-Learning is less stable than policy gradients for differentiable decision trees, a full list of my references/sources, and more thorough comparisons, etc. check out the full paper: Optimization Methods for Interpretable Differentiable Decision Trees in Reinforcement Learning. Why aren’t normal neural networks interpretable?