From Kicking To Causality: Simulating Infant Agency Detection With A Robust Intrinsic Reward

Abstract

While human infants robustly discover their own causal efficacy, standard reinforcement learning agents remain brittle, as their reliance on correlation-based rewards fails in noisy, ecologically valid scenarios. To address this, we introduce the Causal Action Influence Score (CAIS), a novel intrinsic reward rooted in causal inference. CAIS quantifies an action's influence by measuring the 1-Wasserstein distance between the learned distribution of sensory outcomes conditional on that action, \(p(h|a)\), and the baseline outcome distribution, \(p(h)\). This divergence provides a robust reward that isolates the agent's causal impact from confounding environmental noise. We test our approach in a simulated infant-mobile environment where correlation-based perceptual rewards fail completely when the mobile is subjected to external forces. In stark contrast, CAIS enables the agent to filter this noise, identify its influence, and learn the correct policy. Furthermore, the high-quality predi

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyxu2025from

Related papers

• Goal Discovery With Causal Capacity For Efficient Reinforcement Learning (2025)0.00
• Reducing Action Space For Deep Reinforcement Learning Via Causal Effect Estimation (2025)0.00
• Learning By Doing: An Online Causal Reinforcement Learning Framework With Causal-aware Policy (2024)1.56
• Disentangling Causal Effects For Hierarchical Reinforcement Learning (2020)0.00
• Resolving Spurious Correlations In Causal Models Of Environments Via Interventions (2020)0.00
• Breaking Habits: On The Role Of The Advantage Function In Learning Causal State Representations (2025)0.00
• Causal Influence Detection For Improving Efficiency In Reinforcement Learning (2021)0.00
• Explainable Reinforcement Learning Through A Causal Lens (2019)16.69