37
100%
master: 100%

Ran 08 Sep 2019 04:38PM UTC

Jobs 1

Files 21

Run time 2s

Badge

Embed ▾

pending completion

Build # 37

Build Type

push

travis-ci

Committed by

SwamyDev

Commit Message

Implement first RL learning test

These automated tests using a most simple environment make sure that the
REINFORCE algorithm is actually learning something and converging
properly. They can also be used for fast diagnosis and understanding of
how the mechanics of RL work. Because the environment is so simple, a
fast iteration cycle and step by step debugging is possible. Still it
can shed light on many issues typically encountered when designing RL
algorithm (i.e. normalization errors). It also gives a feel on what
makes an algorithm stable and what not.

Run Details

0 of 470 relevant lines covered (0.0%)

0.0 hits per line

Jobs

ID	Job ID	Ran	Files	Coverage
1	37.1	08 Sep 2019 04:38PM UTC	0	0.0	Travis Job 37.1

Source Files on build 37

Detailed source file information is not available for this build.

SwamyDev / reinforcement / 37
100%
master: 100%

README BADGES
x

Markdown

Textile

RDoc

HTML

Rst

Jobs

Source Files on build 37

SwamyDev / reinforcement / 37 100% master: 100%

README BADGES x

Markdown

Textile

RDoc

HTML

Rst

Jobs

Source Files on build 37

SwamyDev / reinforcement / 37
100%
master: 100%

README BADGES
x