AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Explainability Via Causal Self-Talk

Nicholas Andrew Roy, Junkyung Kim, Neil Charles Rabinowitz

NeurIPS 2022 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Boundedly rational agent modeling · 1 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
train with Causal Self-Talk (any variant) instead of ordinary decoderOrd-Dec · DaxDucks one-hotcausal faithfulnessImproved
re-route z back to internal state (RR-Dec) instead of ordinary decoderOrd-Dec · DaxDucks one-hotcausal faithfulnessNo clear effect
use CST instead of baseline decodersOrd-Dec and RR-Dec · DaxDucks one-hotcorrelational faithfulnessNo clear effect
use CST-RL (online interventions with RL) instead of other CST variantsCST · DaxDucks languagecausal faithfulnessImproved
use CST-MR (memory reversion) variantCST · DaxDucks languagecausal faithfulnessHurt
use language messages instead of one-hot messagesCST · DaxDucksfaithfulnessHurt
inject message z' about tag location at each trialCST agent · DaxDucks with shuffled tagsreturnImproved

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