Fix UncertaintyReward bug and improve ExpectedKLDivergence

[timothy-glover]

This pull request addresses an issue when constructing GroundTruthState for generating detections in the UncertaintyReward class that was adversely affecting sensor management performance when using this reward. There are a number of reasons for these changes:

1. Fix the issue where the detections dict would be populated with repeated detections of one track instead of each detectable track, causing the sensor manager to only focus on one track in sensor management for multiple tracks.
2. Pass all tracks as GroundTruthState into sensor.measure such that sensor specific behaviours when detecting multiple targets can be maintained in sensor management.
3. Create a mapping from GroundTruthState to predicted_track such that the prediction object can be passed to the updater rather than the GroundTruthState within detection.groundtruth_path.

Relevant parts of these changes have also been migrated to the ExpectedKLDivergence reward where appropriate, to allow sensor.measure to also operate on multiple tracks at once.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 94.15%. Comparing base (92dae99) to head (a6e0e46).
Report is 36 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1066      +/-   ##
==========================================
- Coverage   94.19%   94.15%   -0.04%     
==========================================
  Files         207      207              
  Lines       13465    13467       +2     
  Branches     2740     2742       +2     
==========================================
- Hits        12683    12680       -3     
- Misses        530      532       +2     
- Partials      252      255       +3     

Flag	Coverage Δ
integration	67.68% <100.00%> (-0.03%)	⬇️
unittests	90.21% <100.00%> (-0.04%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

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