Quiz collegato alla guida · Medio Livello
Quiz sulla valutazione off-policy da dati registrati
Applica l'inverse propensity weighting e identifica sovrapposizione, varianza e requisiti di logging che limitano le stime di policy controfattuale.
Domanda 1 di 8
Cosa stima la valutazione off-policy?
Anteprima di ogni domanda8 domande
Le risposte e le spiegazioni vengono visualizzate mentre rispondi al quiz.
- Cosa stima la valutazione off-policy?
- A target policy's outcomes using data generated by another policy
- The training accuracy of the logging model
- A model's causal feature effects
- The total number of logged requests
- Perché l'IPS divide per la propensione di registrazione?
- To make rewards nonnegative
- To reweight observed actions according to how likely the old policy was to choose them
- To eliminate the need for outcomes
- To estimate the context distribution only
- Cosa succede quando la politica di registrazione assegna una probabilità molto piccola a un'azione scelta?
- The candidate policy is unbiased automatically
- The action outcome becomes known with certainty
- The inverse weight can become large and increase variance
- The reward is set to zero
- Cosa significa la mancanza di supporto per un'azione target?
- Every reward is missing
- The action is always optimal
- The target policy equals the logger
- The logs contain little or no evidence for that action in the context
- Perché riportare la dimensione campionaria effettiva con stime ponderate?
- It changes the propensity values
- It reveals whether a few large weights dominate the information
- It measures the number of policy actions possible
- It proves the reward model is correct
- What tradeoff can clipping IPS weights create?
- Guaranteed unbiasedness
- Higher sample size with no assumptions
- Lower variance but potential bias
- No effect on the estimate
- What must be logged to support ordinary IPS evaluation?
- The candidate policy's future decisions
- Only model predictions
- Only final reward totals
- Action probabilities and outcomes with relevant context
- When might a controlled experiment be needed instead of relying on OPE?
- When the candidate policy acts outside historical support
- Whenever a metric is positive
- When propensities are accurately logged
- When the target matches the logging policy