gaspersic/baselines
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update viz.md

Browse Source
This commit is contained in:
pzhokhov
2018-11-07 14:25:35 -08:00
committed by GitHub
parent 8b95576a92
commit 7bb405c7a7
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/viz/viz.md
View File

@@ -1,4 +1,4 @@
# Loading and visualizing results # Loading and visualizing results ([colab notebook](https://colab.research.google.com/drive/1Wez1SA9PmNkCoYc8Fvl53bhU3F8OffGm))
In order to compare performance of algorithms, we often would like to visualize learning curves (reward as a function of time steps), or some other auxiliary information about learning In order to compare performance of algorithms, we often would like to visualize learning curves (reward as a function of time steps), or some other auxiliary information about learning
aggregated into a plot. Baselines repo provides tools for doing so in several different ways, depending on the goal. aggregated into a plot. Baselines repo provides tools for doing so in several different ways, depending on the goal.
@@ -27,7 +27,7 @@ And you can now start TensorBoard with:
tensorboard --logdir=$OPENAI_LOGDIR tensorboard --logdir=$OPENAI_LOGDIR
``` ```
## Loading summaries of the results ([notebook](https://colab.research.google.com/drive/1Wez1SA9PmNkCoYc8Fvl53bhU3F8OffGm)) ## Loading summaries of the results
If the summary overview provided by tensorboard is not sufficient, and you would like to either access to raw environment episode data, or use complex post-processing notavailable in tensorboard, you can load results into python as [pandas](https://pandas.pydata.org/) dataframes. If the summary overview provided by tensorboard is not sufficient, and you would like to either access to raw environment episode data, or use complex post-processing notavailable in tensorboard, you can load results into python as [pandas](https://pandas.pydata.org/) dataframes.
For instance, the following snippet: For instance, the following snippet: