From cc9580a949b164d7dc664984508253fb80ded4ff Mon Sep 17 00:00:00 2001 From: Gal Leibovich Date: Sun, 22 Oct 2017 16:33:49 +0300 Subject: [PATCH] updated docs with links to github + a few more words on Dashboard functionality --- docs/docs/dashboard.md | 3 +++ docs/docs/index.md | 6 ++++++ 2 files changed, 9 insertions(+) diff --git a/docs/docs/dashboard.md b/docs/docs/dashboard.md index 92accaa..c00a1ac 100644 --- a/docs/docs/dashboard.md +++ b/docs/docs/dashboard.md @@ -14,6 +14,9 @@ Coach Dashboard exposes a convenient user interface for visualizing the training

+* Holding the CTRL key, while selecting signals, will allow visualizing more than one signal. +* Signals can be visualized, using either of the Y-axes, in order to visualize signals with different scales. To move a signal to the second Y-axis, select it and press the 'Toggle Second Axis' button. + ### Tracking Statistics diff --git a/docs/docs/index.md b/docs/docs/index.md index 7a79b1e..20702f4 100644 --- a/docs/docs/index.md +++ b/docs/docs/index.md @@ -11,6 +11,12 @@ With Coach, it is possible to model an agent by combining various building block The available environments allow testing the agent in different practical fields such as robotics, autonomous driving, games and more. Coach collects statistics from the training process and supports advanced visualization techniques for debugging the agent being trained. + + +Blog post from the Intel® Nervana™ website can be found [here](https://www.intelnervana.com/reinforcement-learning-coach-intel). + +GitHub repository is [here](https://github.com/NervanaSystems/coach). + ## Design Coach Design