AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Counterfactual Explanations in Sequential Decision Making Under Uncertainty

Stratis Tsirtsis, Abir De, Manuel Gomez Rodriguez

NeurIPS 2021 · Probabilistic and scientific modeling › Molecules and proteins · approach: Counterfactual and statistical explanations · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the optimal dynamic-programming counterfactual policy instead of the Random, Greedy, or Noisy greedy policySequential counterfactual explanations for CBT patient sessions · CBT patient dataaverage counterfactual outcomeImproved
Allow more action changes from the observed sequence by increasing kOptimal counterfactual policy · Synthetic decision-making processrelative difference in expected outcomeImproved
Increase transition uncertainty αOptimal counterfactual policy · Synthetic decision-making processaverage counterfactual outcomeHurt
Increase transition uncertainty αOptimal counterfactual policy · Synthetic decision-making processrelative difference versus observed outcomeImproved
Allow more action changes from the observed sequence by increasing kOptimal counterfactual policy · CBT patient datarelative difference in expected outcomeImproved
Use the Random policy rather than the optimal counterfactual policySequential counterfactual explanations for CBT patient sessions · CBT patient dataaverage counterfactual outcomeHurt
Replace cognitive restructuring techniques sessions with behavioural activation, especially at the start of symptom worseningOne CBT patient, k = 3 · Individual CBT patient sessionaverage counterfactual outcome: 9.5\%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy