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

Update version of imitation replacing rewards.Batch with data.Transitions #25

Closed AdamGleave closed 4 years ago

AdamGleave commented 4 years ago

Upgrade to latest version of imitation. Most API changes are minor. The main one is there is now a Transitions class which can replace our rewards.Batch, so I've gone through and removed that.

codecov[bot] commented 4 years ago

Codecov Report

Merging #25 into master will not change coverage. The diff coverage is 100.00%.

Impacted file tree graph

@@            Coverage Diff            @@
##            master       #25   +/-   ##
=========================================
  Coverage   100.00%   100.00%           
=========================================
  Files           11        11           
  Lines          555       557    +2     
=========================================
+ Hits           555       557    +2     
Impacted Files Coverage Δ
tests/test_canonical_sample.py 100.00% <100.00%> (ø)
tests/test_rewards.py 100.00% <100.00%> (ø)
tests/test_synthetic.py 100.00% <100.00%> (ø)

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 c6ebe37...3fcc4da. Read the comment docs.