1
66%
master: 66%

Ran 07 Jun 2017 12:56PM UTC

Files 26

Run time 1s

Badge

Embed ▾

Committed 07 Jun 2017 12:48PM UTC coverage: 74.049%. First build

Job # 81.1

Build Type

push

travis-ci

Committed by

tspooner

Commit Message

Replace pi_target method with evaluate_policy

The pi_target method wasn't well defined for on-policy control
algorithms. It was just being used to evaluate a greedy policy during
evaluation. For more clarity it has been replaced with a method
evaluate_policy which takes a reference to any policy trait object and
evaluates that against the algorithm's internal components. This is
actually more general since it will allow a user construct an agent that
learns an explicitly stochastic policy.

Run Details

1110 of 1499 relevant lines covered (74.05%)

0.74 hits per line

tspooner / rsrl / 81 / 1
66%
master: 66%

README BADGES
x

Markdown

Textile

RDoc

HTML

Rst

Source Files on job 81.1

tspooner / rsrl / 81 / 1 66% master: 66%

README BADGES x

Markdown

Textile

RDoc

HTML

Rst

Source Files on job 81.1

tspooner / rsrl / 81 / 1
66%
master: 66%

README BADGES
x