Do as the Romans Do: Learning Universal Behaviors from Heterogeneous Agents

arXiv:2606.18537 · cs.LG · Submitted 2026-06-16 · Read on arXiv

cs.LG

Submitted: 2026-06-16

Updated: 2026-10-02

Code: https://github.com/arama-Foundation/Gymnasium-Robotics

Terminology

• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• General Reward Inference and Disentanglement — 1× in this paper
• Reward Function — 1× in this paper · explained in 3 episodes

Sources

• Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience
• Learning Probabilistic Responsibility Allocations for Multi-Agent Interactions

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