Interpretability in realistic environments

[AdamGleave]

Apply sparsification techniques to higher-dimensional, more realistic environments than the simple evaulating_rewards/PointMassLine-v0 used so far.

[codecov]

Codecov Report

❌ Patch coverage is 60.43956% with 72 lines in your changes missing coverage. Please review.
✅ Project coverage is 82.70%. Comparing base (d1a4ae1) to head (ad16879).
⚠️ Report is 32 commits behind head on master.

Files with missing lines	Patch %	Lines
src/evaluating_rewards/interpretability.py	0.00%	53 Missing ⚠️
src/evaluating_rewards/scripts/expert_demos.py	0.00%	16 Missing ⚠️
src/evaluating_rewards/envs/core.py	90.00%	2 Missing ⚠️
src/evaluating_rewards/scripts/model_comparison.py	50.00%	1 Missing ⚠️

❌ Your project check has failed because the head coverage (83.16%) is below the target coverage (100.00%). You can increase the head coverage or adjust the target coverage.

Additional details and impacted files

@@            Coverage Diff             @@
##           master      #14      +/-   ##
==========================================
- Coverage   84.34%   82.70%   -1.65%     
==========================================
  Files          45       48       +3     
  Lines        2906     3035     +129     
==========================================
+ Hits         2451     2510      +59     
- Misses        455      525      +70     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.