EvaluationReport

Models & Types · AiDotNet.Agentic.SelfImproving

Aggregate statistics from evaluating a set of trajectories: how many were scored, the reward distribution, and the fraction that met a pass threshold. This is the scoreboard a self-improvement loop watches to know whether it is getting better.

For Beginners

The report card for a batch of runs — average score, best and worst, and what percentage “passed”. Compare reports before and after a change to see whether the agents improved.

Constructors

Constructor Summary
EvaluationReport(int count, double meanReward, double minReward, double maxReward, double passRate, double passThreshold) Initializes a new report.

Properties

Property Summary
double MaxReward { get; } Gets the maximum reward (0 when none).
double MeanReward { get; } Gets the mean reward across scored trajectories (0 when none).
double MinReward { get; } Gets the minimum reward (0 when none).
double PassRate { get; } Gets the fraction of trajectories meeting the pass threshold (0–1).
double PassThreshold { get; } Gets the threshold used to compute PassRate.
int Count { get; } Gets the number of trajectories scored.