45
99%
master: 99%

Ran 11 Mar 2020 06:59PM UTC

Jobs 1

Files 14

Run time 2s

Badge

Embed ▾

pending completion

Build # 45

Build Type

push

travis-ci-com

Committed by

SwamyDev

Commit Message

Improve exploration logic of MADDPG agent

By allowing preheat steps which are completely random the agent can
observe a more diverse set of states. Otherwise it wouldn't see that
much because it tends to crash early on into a local minimum. With these
trajectories in the replay buffer it seems to be better abel to get out
of it again. Additionally I've added static noise to the training. This
should also help in exploring and getting the agent out of local minima.
For now I just use a fixed value.

Run Details

583 of 652 relevant lines covered (89.42%)

0.89 hits per line

Jobs

ID	Job ID	Ran	Files	Coverage
1	45.1	11 Mar 2020 06:59PM UTC	0	89.42	Travis Job 45.1

Source Files on build 45

Detailed source file information is not available for this build.

SwamyDev / udacity-deep-rl-navigation / 45
99%
master: 99%

README BADGES
x

Markdown

Textile

RDoc

HTML

Rst

Jobs

Source Files on build 45

SwamyDev / udacity-deep-rl-navigation / 45 99% master: 99%

README BADGES x

Markdown

Textile

RDoc

HTML

Rst

Jobs

Source Files on build 45

SwamyDev / udacity-deep-rl-navigation / 45
99%
master: 99%

README BADGES
x