Implicit Neural Representations of Individual Behavior

Andrew Kang, Priya Narasimhan

Keywords: implicit neural representations, policy representation learning, imitation learning, behavioral cloning, offline reinforcement learning, self-supervised learning, out-of-distribution generalization, trajectory modeling, policy identification

TL;DR: We introduce Behavioral INR, which adapts implicit neural representations from vision to behavior: instead of mapping coordinates to RGB values, it represents a policy as a state-action function mapping states to actions.

Abstract: We study policy representation learning from unlabeled multi-policy behavioral data, where each episode is generated by a fixed but unobserved policy. We introduce Behavioral INR, a self-supervised generative model that adapts implicit neural representations from vision to behavior: instead of mapping coordinates to RGB values, it represents a policy as a state-action function mapping states to actions. An episode-level latent modulates this function through FiLM layers, yielding a generative prior over policies and enabling policy identity inference without labels. We also define policy-level out-of-distribution (OOD) shifts along state- and action-distribution axes, which arise when policies overlap but are not captured by standard agent- or environment-level OOD settings. Across synthetic GRF data, Seek-Avoid, MuJoCo, chess, Formula 1, and robotic manipulation, Behavioral INR most consistently improves policy identifiability in harder continuous state-action settings, especially when longer episodes, more policies, and OOD splits reduce marginal shortcuts.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 184