Coupled Distributional Random Expert Distillation for World Model Online Imitation Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Shangzhe, Huang, Zhiao, Su, Hao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909980546826240
author Li, Shangzhe
Huang, Zhiao
Su, Hao
author_facet Li, Shangzhe
Huang, Zhiao
Su, Hao
contents Imitation Learning (IL) has achieved remarkable success across various domains, including robotics, autonomous driving, and healthcare, by enabling agents to learn complex behaviors from expert demonstrations. However, existing IL methods often face instability challenges, particularly when relying on adversarial reward or value formulations in world model frameworks. In this work, we propose a novel approach to online imitation learning that addresses these limitations through a reward model based on random network distillation (RND) for density estimation. Our reward model is built on the joint estimation of expert and behavioral distributions within the latent space of the world model. We evaluate our method across diverse benchmarks, including DMControl, Meta-World, and ManiSkill2, showcasing its ability to deliver stable performance and achieve expert-level results in both locomotion and manipulation tasks. Our approach demonstrates improved stability over adversarial methods while maintaining expert-level performance.
format Preprint
id arxiv_https___arxiv_org_abs_2505_02228
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Coupled Distributional Random Expert Distillation for World Model Online Imitation Learning
Li, Shangzhe
Huang, Zhiao
Su, Hao
Machine Learning
Artificial Intelligence
Imitation Learning (IL) has achieved remarkable success across various domains, including robotics, autonomous driving, and healthcare, by enabling agents to learn complex behaviors from expert demonstrations. However, existing IL methods often face instability challenges, particularly when relying on adversarial reward or value formulations in world model frameworks. In this work, we propose a novel approach to online imitation learning that addresses these limitations through a reward model based on random network distillation (RND) for density estimation. Our reward model is built on the joint estimation of expert and behavioral distributions within the latent space of the world model. We evaluate our method across diverse benchmarks, including DMControl, Meta-World, and ManiSkill2, showcasing its ability to deliver stable performance and achieve expert-level results in both locomotion and manipulation tasks. Our approach demonstrates improved stability over adversarial methods while maintaining expert-level performance.
title Coupled Distributional Random Expert Distillation for World Model Online Imitation Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.02228