From Kicking to Causality: Simulating Infant Agency Detection with a Robust Intrinsic Reward
This addresses the challenge of developing robust agency detection for autonomous systems, offering a psychologically plausible framework, though it appears incremental as it builds on causal inference methods.
The paper tackled the problem of reinforcement learning agents failing in noisy environments by introducing the Causal Action Influence Score (CAIS), an intrinsic reward based on causal inference, which enabled an agent to filter noise and learn correct policies in a simulated infant-mobile scenario where correlation-based rewards failed completely.
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 predictive model learned for CAIS allows our agent, when augmented with a surprise signal, to successfully reproduce the "extinction burst" phenomenon. We conclude that explicitly inferring causality is a crucial mechanism for developing a robust sense of agency, offering a psychologically plausible framework for more adaptive autonomous systems.