AI Paper Atlas

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

Passive learning of active causal strategies in agents and language models

Andrew Kyle Lampinen, Stephanie C.Y. Chan, Ishita Dasgupta, Andrew Joohun Nam, Jane X Wang

NeurIPS 2023 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Language-grounded reinforcement agents · 10 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
remove active interventional exploration phase (skip or observe only) (ablation)imitation agent · causal DAG environmentrewardHurt
replace skipped exploration with observation-only phase (ablation)imitation agent · causal DAG environmentrewardImproved
reduce training DAG structures from 1277 to 428 (ablation)imitation agent · held-out causal DAG evaluationgeneralization: 1277 -> 428 structuresHurt
reduce training DAG structures from 1277 to 195 (ablation)imitation agent · held-out causal DAG evaluationgeneralization: 1277 -> 195 structuresHurt
train on linear DAGs, evaluate on nonlinear DAGs (ablation)imitation agent · causal DAG environmentfraction of optimal reward: over 75% of optimalMixed
add auxiliary language explanation prediction (ablation)imitation agent · odd-one-out environmentslearning and generalizationImproved
train to predict explanations focused on one feature on confounded data (ablation)imitation agent · deconfounded odd-one-out evaluationOOD choice following explained featureImproved
include explanations and reasoning traces in few-shot prompt (ablation)Chinchilla 70B · odd-one-out LM, held-out dimensiongeneralizationImproved
use only explanations or only reasoning (not both) in prompt (ablation)Chinchilla 70B · odd-one-out LMaverage performanceMixed
make expert policy in examples switch to exploiting after finding correct dimension (ablation)Chinchilla 70B · odd-one-out LM, texture held outgeneralizationHurt
train on subsets of variables with relevance cueimitation agent · adaptive experimentation, n=10 variablesoptimal exploration on held-out variable setsImproved

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