Guardado en:
Detalles Bibliográficos
Autores principales: He, Bowei, Sun, Zexu, Liu, Jinxin, Zhang, Shuai, Chen, Xu, Ma, Chen
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:https://arxiv.org/abs/2310.04706
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911742925209600
author He, Bowei
Sun, Zexu
Liu, Jinxin
Zhang, Shuai
Chen, Xu
Ma, Chen
author_facet He, Bowei
Sun, Zexu
Liu, Jinxin
Zhang, Shuai
Chen, Xu
Ma, Chen
contents In offline imitation learning (IL), an agent aims to learn an optimal expert behavior policy without additional online environment interactions. However, in many real-world scenarios, such as robotics manipulation, the offline dataset is collected from suboptimal behaviors without rewards. Due to the scarce expert data, the agents usually suffer from simply memorizing poor trajectories and are vulnerable to variations in the environments, lacking the capability of generalizing to new environments. To automatically generate high-quality expert data and improve the generalization ability of the agent, we propose a framework named \underline{O}ffline \underline{I}mitation \underline{L}earning with \underline{C}ounterfactual data \underline{A}ugmentation (OILCA) by doing counterfactual inference. In particular, we leverage identifiable variational autoencoder to generate \textit{counterfactual} samples for expert data augmentation. We theoretically analyze the influence of the generated expert data and the improvement of generalization. Moreover, we conduct extensive experiments to demonstrate that our approach significantly outperforms various baselines on both \textsc{DeepMind Control Suite} benchmark for in-distribution performance and \textsc{CausalWorld} benchmark for out-of-distribution generalization. Our code is available at \url{https://github.com/ZexuSun/OILCA-NeurIPS23}.
format Preprint
id arxiv_https___arxiv_org_abs_2310_04706
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Offline Imitation Learning with Variational Counterfactual Reasoning
He, Bowei
Sun, Zexu
Liu, Jinxin
Zhang, Shuai
Chen, Xu
Ma, Chen
Machine Learning
In offline imitation learning (IL), an agent aims to learn an optimal expert behavior policy without additional online environment interactions. However, in many real-world scenarios, such as robotics manipulation, the offline dataset is collected from suboptimal behaviors without rewards. Due to the scarce expert data, the agents usually suffer from simply memorizing poor trajectories and are vulnerable to variations in the environments, lacking the capability of generalizing to new environments. To automatically generate high-quality expert data and improve the generalization ability of the agent, we propose a framework named \underline{O}ffline \underline{I}mitation \underline{L}earning with \underline{C}ounterfactual data \underline{A}ugmentation (OILCA) by doing counterfactual inference. In particular, we leverage identifiable variational autoencoder to generate \textit{counterfactual} samples for expert data augmentation. We theoretically analyze the influence of the generated expert data and the improvement of generalization. Moreover, we conduct extensive experiments to demonstrate that our approach significantly outperforms various baselines on both \textsc{DeepMind Control Suite} benchmark for in-distribution performance and \textsc{CausalWorld} benchmark for out-of-distribution generalization. Our code is available at \url{https://github.com/ZexuSun/OILCA-NeurIPS23}.
title Offline Imitation Learning with Variational Counterfactual Reasoning
topic Machine Learning
url https://arxiv.org/abs/2310.04706