search

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

Handle episode termination for potential shaping #29

Closed AdamGleave closed 4 years ago

codecov[bot] commented 4 years ago

Codecov Report

Merging #29 into master will increase coverage by 0.32%. The diff coverage is 94.85%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master      #29      +/-   ##
==========================================
+ Coverage   87.66%   87.98%   +0.32%     
==========================================
  Files          55       55              
  Lines        3736     3830      +94     
==========================================
+ Hits         3275     3370      +95     
+ Misses        461      460       -1
Impacted Files Coverage Δ
...ards/analysis/dissimilarity_heatmaps/cli_common.py 67.96% <0.00%> (ø)
src/evaluating_rewards/experiments/env_rewards.py 0.00% <ø> (ø)
src/evaluating_rewards/experiments/monte_carlo.py 0.00% <0.00%> (ø)
src/evaluating_rewards/analysis/results.py 69.23% <50.00%> (ø)
src/evaluating_rewards/serialize.py 73.52% <50.00%> (ø)
src/evaluating_rewards/experiments/synthetic.py 83.76% <66.66%> (ø)
src/evaluating_rewards/rewards.py 96.34% <96.72%> (+0.86%) :arrow_up:
...lysis/dissimilarity_heatmaps/plot_canon_heatmap.py 97.10% <100.00%> (ø)
...alysis/dissimilarity_heatmaps/plot_epic_heatmap.py 96.29% <100.00%> (ø)
...s/dissimilarity_heatmaps/plot_gridworld_heatmap.py 92.30% <100.00%> (ø)
... and 16 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 6347f38...68ea60d. Read the comment docs.