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

Tune algorithms for PointMass transfer learning #6

Closed AdamGleave closed 4 years ago

codecov[bot] commented 4 years ago

Codecov Report

Merging #6 into master will decrease coverage by 0.04%. The diff coverage is 66.66%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master       #6      +/-   ##
==========================================
- Coverage   71.36%   71.32%   -0.05%     
==========================================
  Files          39       39              
  Lines        2375     2382       +7     
==========================================
+ Hits         1695     1699       +4     
- Misses        680      683       +3
Impacted Files Coverage Δ
src/evaluating_rewards/envs/mujoco.py 98.16% <ø> (-0.02%) :arrow_down:
src/evaluating_rewards/scripts/expert_demos.py 0% <0%> (ø) :arrow_up:
...rc/evaluating_rewards/scripts/train_adversarial.py 0% <0%> (ø) :arrow_up:
src/evaluating_rewards/scripts/eval_policy.py 0% <0%> (ø) :arrow_up:
src/evaluating_rewards/preferences.py 99.24% <100%> (ø) :arrow_up:
...rc/evaluating_rewards/scripts/train_preferences.py 97.82% <100%> (+0.15%) :arrow_up:
src/evaluating_rewards/scripts/train_regress.py 95.12% <100%> (ø) :arrow_up:
src/evaluating_rewards/rewards.py 97.11% <100%> (ø) :arrow_up:
src/evaluating_rewards/scripts/script_utils.py 56.25% <44.44%> (-3.01%) :arrow_down:

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 5e2178c...3e359d7. Read the comment docs.