Fix UncertaintyReward bug and improve ExpectedKLDivergence #1066
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This pull request addresses an issue when constructing
GroundTruthState
for generating detections in theUncertaintyReward
class that was adversely affecting sensor management performance when using this reward. There are a number of reasons for these changes: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.GroundTruthState
intosensor.measure
such that sensor specific behaviours when detecting multiple targets can be maintained in sensor management.GroundTruthState
topredicted_track
such that the prediction object can be passed to the updater rather than theGroundTruthState
withindetection.groundtruth_path
.Relevant parts of these changes have also been migrated to the
ExpectedKLDivergence
reward where appropriate, to allowsensor.measure
to also operate on multiple tracks at once.