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

Rewards and heatmaps for gridworlds #31

Closed AdamGleave closed 4 years ago

codecov[bot] commented 4 years ago

Codecov Report

Merging #31 into master will decrease coverage by 0.15%. The diff coverage is 91.35%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master      #31      +/-   ##
==========================================
- Coverage   87.84%   87.68%   -0.16%     
==========================================
  Files          57       57              
  Lines        3958     3988      +30     
==========================================
+ Hits         3477     3497      +20     
- Misses        481      491      +10     
Impacted Files Coverage Δ
src/evaluating_rewards/analysis/stylesheets.py 71.42% <ø> (ø)
tests/test_scripts.py 100.00% <ø> (ø)
...s/analysis/reward_figures/plot_gridworld_reward.py 88.00% <77.27%> (-9.78%) :arrow_down:
...ards/analysis/dissimilarity_heatmaps/cli_common.py 77.47% <85.71%> (+0.37%) :arrow_up:
...s/dissimilarity_heatmaps/plot_gridworld_heatmap.py 91.74% <91.66%> (-0.57%) :arrow_down:
...ewards/analysis/dissimilarity_heatmaps/heatmaps.py 82.55% <100.00%> (-8.14%) :arrow_down:
...c/evaluating_rewards/analysis/gridworld_rewards.py 100.00% <100.00%> (ø)
...nalysis/reward_figures/gridworld_reward_heatmap.py 98.30% <100.00%> (+2.07%) :arrow_up:
src/evaluating_rewards/tabular.py 72.91% <100.00%> (ø)
tests/test_util.py 100.00% <100.00%> (ø)
... and 2 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 7b5c0b7...49b165b. Read the comment docs.