Task Inference Beyond Least Squares in Behavioral Foundation Models

arXiv:2610.05350 · cs.LG · Submitted 2026-10-04 · Read on arXiv

cs.LG

Submitted: 2026-10-04

Updated: 2026-10-04

Project page: https://embodiedai-ntu.github.io/BLS

Terminology

• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes

Sources

• Learning Successor States and Goal-Dependent Values: A Mathematical Viewpoint
• Which Features are Best for Successor Features?
• RLZero: Direct Policy Inference from Language Without In-Domain Supervision
• Fast Adaptation with Behavioral Foundation Models
• DeepMind Control Suite

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks