AI Paper Atlas

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

Tell me why! Explanations support learning relational and causal structure

Andrew K Lampinen, Nicholas Roy, Ishita Dasgupta, Stephanie Cy Chan, Allison Tam, James Mcclelland, Chen Yan, Adam Santoro, Neil C Rabinowitz, Jane Wang, Felix Hill

ICML 2022 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Language-grounded reinforcement agents · 9 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
Add property and reward explanation prediction targetsIMPALA RL agent · Perceptual odd-one-out 2Dperformance (% correct): 61.9\pm 2.2 -> 91.3 \pm 0.7Improved
Add property and reward explanation prediction targetsIMPALA RL agent · Perceptual odd-one-out 3Dperformance (% correct): 29.5\pm 0.7 -> 92.7 \pm 1.4Improved
Add single-dimension color explanationsIMPALA RL agent · Deconfounding: choose colorperformance (% correct): 55.4 \pm 2.6 -> 95.5\pm 0.9Improved
Add single-dimension shape explanationsIMPALA RL agent · Deconfounding: choose shapeperformance (% correct): 24.2\pm 7.6 -> 87.5\pm 2.9Improved
Add single-dimension texture explanationsIMPALA RL agent · Deconfounding: choose textureperformance (% correct): 15.4\pm 6.7 -> 86.2\pm 0.9Improved
Add behavior- and context-relevant explanation predictionIMPALA RL agent · Meta-learning easy levelsperformance (% correct): 24.0\pm 0.6 -> 96.9 \pm 0.3Improved
Add behavior- and context-relevant explanation predictionIMPALA RL agent · Meta-learning hard levelsperformance (% correct): 24.6\pm 1.2 -> 90.5 \pm 1.6Improved
Replace prediction targets with explanations provided as inputs (ablation)IMPALA RL agent · Odd-one-out tasksperformanceHurt
Add both property and reward explanations instead of using either type alone (ablation)IMPALA RL agent · Perceptual odd-one-out 2Dlearning speedImproved
Use reward explanations rather than property explanations alone (ablation)IMPALA RL agent · Meta-learning hard levelslearningImproved
Use behavior- and context-relevant explanations instead of behavior-irrelevant explanations (ablation)IMPALA RL agent · Meta-learning easy and hard levelslearningImproved
Use behavior- and context-relevant explanations instead of context-irrelevant explanations (ablation)IMPALA RL agent · Odd-one-out taskslearningImproved

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