sritchie / scala-rl

Functional Reinforcement Learning in Scala.
https://www.scalarl.com
Apache License 2.0
26 stars 5 forks source link

Convert Bandits to use ActionValue estimators #53

Closed sritchie closed 4 years ago

codecov[bot] commented 4 years ago

Codecov Report

Merging #53 into develop will decrease coverage by 2.1%. The diff coverage is 0%.

Impacted file tree graph

@@             Coverage Diff             @@
##           develop      #53      +/-   ##
===========================================
- Coverage    25.85%   23.75%   -2.11%     
===========================================
  Files           42       42              
  Lines          905     1023     +118     
  Branches        30       37       +7     
===========================================
+ Hits           234      243       +9     
- Misses         671      780     +109
Impacted Files Coverage Δ
...rl-core/src/main/scala/io/samritchie/rl/Util.scala 28% <ø> (ø) :arrow_up:
.../scala/io/samritchie/rl/policy/bandit/Greedy.scala 0% <ø> (ø) :arrow_up:
...rc/main/scala/io/samritchie/rl/book/Chapter2.scala 0% <ø> (ø) :arrow_up:
.../scala/io/samritchie/rl/value/ActionValueMap.scala 0% <ø> (ø) :arrow_up:
...cala/io/samritchie/rl/policy/bandit/Gradient.scala 0% <0%> (ø) :arrow_up:
...ain/scala/io/samritchie/rl/policy/bandit/UCB.scala 0% <0%> (ø) :arrow_up:
...re/src/main/scala/io/samritchie/rl/Evaluator.scala 84.61% <0%> (-7.06%) :arrow_down:
...re/src/main/scala/io/samritchie/rl/util/Grid.scala 84.61% <0%> (-0.76%) :arrow_down:
...rc/main/scala/io/samritchie/connectfour/Game.scala 0% <0%> (ø) :arrow_up:
... and 5 more

Continue to review full report at Codecov.

Legend - Click here to learn more Δ = absolute <relative> (impact), ø = not affected, ? = missing data Powered by Codecov. Last update 08cd366...3c2bb48. Read the comment docs.