From be433fdb8334b30fb4688b5ca05e755a6c76b82f Mon Sep 17 00:00:00 2001
From: Peter Zhokhov <peterz@openai.com>
Date: Mon, 29 Oct 2018 15:53:50 -0700
Subject: [PATCH] viz docs

---
 docs/viz/viz.md | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)
 create mode 100644 docs/viz/viz.md

diff --git a/docs/viz/viz.md b/docs/viz/viz.md
new file mode 100644
index 0000000..be4d55d
--- /dev/null
+++ b/docs/viz/viz.md
@@ -0,0 +1,27 @@
+# Loading and visualizing results 
+In order to compare performance of algorithms, we often would like to vizualise learning curves (reward as a function of timesteps), or some other auxiliary information about learining
+aggregated into a plot. Baselines repo provides tools for doing so in several different ways, depending on the goal. 
+
+## Preliminaries
+For all algorithms in baselines directory in which summary data is saved is defined by logger. By default, a folder  `$TMPDIR/openai-<date>-<time>` is used; 
+you can see the location of logger directory at the beginning of the training in the message like this:
+
+```
+Logging to /var/folders/mq/tgrn7bs17s1fnhlwt314b2fm0000gn/T/openai-2018-10-29-15-03-13-537078
+```
+The location can be changed by changing `OPENAI_LOGDIR` environment variable; for instance:
+```
+export OPENAI_LOGDIR=$HOME/models/mujoco-ppo-humanoid
+python -m baselines.run --alg=ppo2 --env=Humanoid-v2
+```
+will log data to `~/models/mujoco-ppo-humanoid`. 
+
+## Using TensorBoard
+One of the most straightforward ways to visualize data is to use TensorBoard (). Baselines logger can dump data in tensorboard-compatible format.
+
+## Loading summaries of the results
+
+## Plotting: standalone 
+
+## Plotting: jupyter notebook
+