HumanCompatibleAI / evaluating-rewards

Library to compare and evaluate reward functions
https://arxiv.org/abs/2006.13900
Apache License 2.0
61 stars 7 forks source link

Script to plot divergence heatmap #8

Closed AdamGleave closed 4 years ago

AdamGleave commented 4 years ago
codecov[bot] commented 4 years ago

Codecov Report

Merging #8 into master will increase coverage by 10.18%. The diff coverage is 76.28%.

Impacted file tree graph

@@             Coverage Diff             @@
##           master       #8       +/-   ##
===========================================
+ Coverage   71.32%   81.51%   +10.18%     
===========================================
  Files          39       41        +2     
  Lines        2382     2461       +79     
===========================================
+ Hits         1699     2006      +307     
+ Misses        683      455      -228
Impacted Files Coverage Δ
tests/test_comparisons.py 100% <ø> (ø) :arrow_up:
src/evaluating_rewards/envs/point_mass.py 83.23% <ø> (ø) :arrow_up:
tests/test_scripts.py 100% <100%> (ø) :arrow_up:
src/evaluating_rewards/serialize.py 73.01% <100%> (+2.32%) :arrow_up:
src/evaluating_rewards/scripts/model_comparison.py 73.17% <100%> (ø) :arrow_up:
src/evaluating_rewards/analysis/stylesheets.py 100% <100%> (ø)
src/evaluating_rewards/scripts/script_utils.py 53.33% <66.66%> (-2.92%) :arrow_down:
src/evaluating_rewards/analysis/results.py 69.23% <69.23%> (ø)
...uating_rewards/analysis/plot_divergence_heatmap.py 70% <70%> (ø)
src/evaluating_rewards/analysis/visualize.py 83.15% <83.15%> (ø)
... 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 3a032c5...e25568d. Read the comment docs.