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

Switch to free mjkey Dockerfile #54

Open AdamGleave opened 2 years ago

codecov[bot] commented 2 years ago

Codecov Report

Merging #54 (3fb1403) into master (7b99ec9) will decrease coverage by 0.64%. The diff coverage is 54.54%.

@@            Coverage Diff             @@
##           master      #54      +/-   ##
==========================================
- Coverage   81.49%   80.84%   -0.65%     
==========================================
  Files          69       69              
  Lines        4933     4934       +1     
==========================================
- Hits         4020     3989      -31     
- Misses        913      945      +32
Impacted Files Coverage Δ
src/evaluating_rewards/analysis/results.py 33.02% <0.00%> (-4.59%) :arrow_down:
...ting_rewards/analysis/reward_figures/point_mass.py 79.10% <ø> (ø)
src/evaluating_rewards/distances/epic_sample.py 96.93% <ø> (+4.08%) :arrow_up:
src/evaluating_rewards/distances/npec.py 63.93% <ø> (ø)
src/evaluating_rewards/experiments/synthetic.py 85.60% <ø> (ø)
...ing_rewards/scripts/pipeline/combined_distances.py 32.62% <0.00%> (-20.90%) :arrow_down:
src/evaluating_rewards/scripts/script_utils.py 67.85% <0.00%> (+0.58%) :arrow_up:
tests/test_synthetic.py 100.00% <ø> (ø)
src/evaluating_rewards/distances/common_config.py 92.95% <100.00%> (ø)
src/evaluating_rewards/envs/point_mass.py 83.33% <100.00%> (ø)
... and 12 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 7b99ec9...3fb1403. Read the comment docs.