• Home
  • Features
  • Pricing
  • Docs
  • Announcements
  • Sign In

SwamyDev / reinforcement / 71 / 1
100%
master: 100%

Build:
Build:
LAST BUILD BRANCH: dependabot/pip/tensorflow-1.15.4
DEFAULT BRANCH: master
Ran 15 Sep 2019 06:55PM UTC
Files 21
Run time 1s
Badge
Embed ▾
README BADGES
x

If you need to use a raster PNG badge, change the '.svg' to '.png' in the link

Markdown

Textile

RDoc

HTML

Rst

15 Sep 2019 06:53PM UTC coverage: 100.0%. Remained the same
71.1

push

travis-ci

SwamyDev
Add negative test for baseline usage

This test should make sure, that the environment we test the baseline
with is truly harder without usage of a baseline to reduce variance.
While creating the test, it also turned out that the baseline seems to
work much better without normalization of the returns. I suspect this
results from moving the state values by normalizing it. However, by
just normalizing the advantages, the difference between using a baseline
or not, is much clearer.

The tests are a bit brittle right now, however, they should warrant
further investigation of one of them fails.

470 of 470 relevant lines covered (100.0%)

1.0 hits per line

Source Files on job 71.1
  • Tree
  • List 0
  • Changed 1
  • Source Changed 1
  • Coverage Changed 0
Coverage ∆ File Lines Relevant Covered Missed Hits/Line
  • Back to Build 57
  • Travis Job 71.1
  • b461f675 on github
  • Prev Job for on learning-tests (#69.1)
  • Next Job for on learning-tests (#73.1)
STATUS · Troubleshooting · Open an Issue · Sales · Support · CAREERS · ENTERPRISE · START FREE · SCHEDULE DEMO
ANNOUNCEMENTS · TWITTER · TOS & SLA · Supported CI Services · What's a CI service? · Automated Testing

© 2026 Coveralls, Inc