Expert Proximity as Surrogate Rewards for Single Demonstration Imitation Learning

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chiang, Chia-Cheng, Lan, Li-Cheng, Sun, Wei-Fang, Feng, Chien, Hsieh, Cho-Jui, Lee, Chun-Yi
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914860328026112
author Chiang, Chia-Cheng
Lan, Li-Cheng
Sun, Wei-Fang
Feng, Chien
Hsieh, Cho-Jui
Lee, Chun-Yi
author_facet Chiang, Chia-Cheng
Lan, Li-Cheng
Sun, Wei-Fang
Feng, Chien
Hsieh, Cho-Jui
Lee, Chun-Yi
contents In this paper, we focus on single-demonstration imitation learning (IL), a practical approach for real-world applications where acquiring multiple expert demonstrations is costly or infeasible and the ground truth reward function is not available. In contrast to typical IL settings with multiple demonstrations, single-demonstration IL involves an agent having access to only one expert trajectory. We highlight the issue of sparse reward signals in this setting and propose to mitigate this issue through our proposed Transition Discriminator-based IL (TDIL) method. TDIL is an IRL method designed to address reward sparsity by introducing a denser surrogate reward function that considers environmental dynamics. This surrogate reward function encourages the agent to navigate towards states that are proximal to expert states. In practice, TDIL trains a transition discriminator to differentiate between valid and non-valid transitions in a given environment to compute the surrogate rewards. The experiments demonstrate that TDIL outperforms existing IL approaches and achieves expert-level performance in the single-demonstration IL setting across five widely adopted MuJoCo benchmarks as well as the "Adroit Door" robotic environment.
format Preprint
id arxiv_https___arxiv_org_abs_2402_01057
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Expert Proximity as Surrogate Rewards for Single Demonstration Imitation Learning
Chiang, Chia-Cheng
Lan, Li-Cheng
Sun, Wei-Fang
Feng, Chien
Hsieh, Cho-Jui
Lee, Chun-Yi
Machine Learning
In this paper, we focus on single-demonstration imitation learning (IL), a practical approach for real-world applications where acquiring multiple expert demonstrations is costly or infeasible and the ground truth reward function is not available. In contrast to typical IL settings with multiple demonstrations, single-demonstration IL involves an agent having access to only one expert trajectory. We highlight the issue of sparse reward signals in this setting and propose to mitigate this issue through our proposed Transition Discriminator-based IL (TDIL) method. TDIL is an IRL method designed to address reward sparsity by introducing a denser surrogate reward function that considers environmental dynamics. This surrogate reward function encourages the agent to navigate towards states that are proximal to expert states. In practice, TDIL trains a transition discriminator to differentiate between valid and non-valid transitions in a given environment to compute the surrogate rewards. The experiments demonstrate that TDIL outperforms existing IL approaches and achieves expert-level performance in the single-demonstration IL setting across five widely adopted MuJoCo benchmarks as well as the "Adroit Door" robotic environment.
title Expert Proximity as Surrogate Rewards for Single Demonstration Imitation Learning
topic Machine Learning
url https://arxiv.org/abs/2402.01057