Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Heyang, Yu, Xingrui, Bossens, David M., Tsang, Ivor W., Gu, Quanquan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908421273419776
author Zhao, Heyang
Yu, Xingrui
Bossens, David M.
Tsang, Ivor W.
Gu, Quanquan
author_facet Zhao, Heyang
Yu, Xingrui
Bossens, David M.
Tsang, Ivor W.
Gu, Quanquan
contents Imitation learning is a central problem in reinforcement learning where the goal is to learn a policy that mimics the expert's behavior. In practice, it is often challenging to learn the expert policy from a limited number of demonstrations accurately due to the complexity of the state space. Moreover, it is essential to explore the environment and collect data to achieve beyond-expert performance. To overcome these challenges, we propose a novel imitation learning algorithm called Imitation Learning with Double Exploration (ILDE), which implements exploration in two aspects: (1) optimistic policy optimization via an exploration bonus that rewards state-action pairs with high uncertainty to potentially improve the convergence to the expert policy, and (2) curiosity-driven exploration of the states that deviate from the demonstration trajectories to potentially yield beyond-expert performance. Empirically, we demonstrate that ILDE outperforms the state-of-the-art imitation learning algorithms in terms of sample efficiency and achieves beyond-expert performance on Atari and MuJoCo tasks with fewer demonstrations than in previous work. We also provide a theoretical justification of ILDE as an uncertainty-regularized policy optimization method with optimistic exploration, leading to a regret growing sublinearly in the number of episodes.
format Preprint
id arxiv_https___arxiv_org_abs_2506_20307
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration
Zhao, Heyang
Yu, Xingrui
Bossens, David M.
Tsang, Ivor W.
Gu, Quanquan
Machine Learning
Artificial Intelligence
Imitation learning is a central problem in reinforcement learning where the goal is to learn a policy that mimics the expert's behavior. In practice, it is often challenging to learn the expert policy from a limited number of demonstrations accurately due to the complexity of the state space. Moreover, it is essential to explore the environment and collect data to achieve beyond-expert performance. To overcome these challenges, we propose a novel imitation learning algorithm called Imitation Learning with Double Exploration (ILDE), which implements exploration in two aspects: (1) optimistic policy optimization via an exploration bonus that rewards state-action pairs with high uncertainty to potentially improve the convergence to the expert policy, and (2) curiosity-driven exploration of the states that deviate from the demonstration trajectories to potentially yield beyond-expert performance. Empirically, we demonstrate that ILDE outperforms the state-of-the-art imitation learning algorithms in terms of sample efficiency and achieves beyond-expert performance on Atari and MuJoCo tasks with fewer demonstrations than in previous work. We also provide a theoretical justification of ILDE as an uncertainty-regularized policy optimization method with optimistic exploration, leading to a regret growing sublinearly in the number of episodes.
title Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.20307