DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation

Jinxin Liu, Xinghong Guo, Zifeng Zhuang, Donglin Wang
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31032-31047, 2024.

Abstract

In this paper, we propose a novel approach called DIffusion-guided DIversity (DIDI) for offline behavioral generation. The goal of DIDI is to learn a diverse set of skills from a mixture of label-free offline data. We achieve this by leveraging diffusion probabilistic models as priors to guide the learning process and regularize the policy. By optimizing a joint objective that incorporates diversity and diffusion-guided regularization, we encourage the emergence of diverse behaviors while maintaining the similarity to the offline data. Experimental results in four decision-making domains (Push, Kitchen, Humanoid, and D4RL tasks) show that DIDI is effective in discovering diverse and discriminative skills. We also introduce skill stitching and skill interpolation, which highlight the generalist nature of the learned skill space. Further, by incorporating an extrinsic reward function, DIDI enables reward-guided behavior generation, facilitating the learning of diverse and optimal behaviors from sub-optimal data.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-liu24s, title = {{DIDI}: Diffusion-Guided Diversity for Offline Behavioral Generation}, author = {Liu, Jinxin and Guo, Xinghong and Zhuang, Zifeng and Wang, Donglin}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {31032--31047}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/liu24s/liu24s.pdf}, url = {https://proceedings.mlr.press/v235/liu24s.html}, abstract = {In this paper, we propose a novel approach called DIffusion-guided DIversity (DIDI) for offline behavioral generation. The goal of DIDI is to learn a diverse set of skills from a mixture of label-free offline data. We achieve this by leveraging diffusion probabilistic models as priors to guide the learning process and regularize the policy. By optimizing a joint objective that incorporates diversity and diffusion-guided regularization, we encourage the emergence of diverse behaviors while maintaining the similarity to the offline data. Experimental results in four decision-making domains (Push, Kitchen, Humanoid, and D4RL tasks) show that DIDI is effective in discovering diverse and discriminative skills. We also introduce skill stitching and skill interpolation, which highlight the generalist nature of the learned skill space. Further, by incorporating an extrinsic reward function, DIDI enables reward-guided behavior generation, facilitating the learning of diverse and optimal behaviors from sub-optimal data.} }
Endnote
%0 Conference Paper %T DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation %A Jinxin Liu %A Xinghong Guo %A Zifeng Zhuang %A Donglin Wang %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-liu24s %I PMLR %P 31032--31047 %U https://proceedings.mlr.press/v235/liu24s.html %V 235 %X In this paper, we propose a novel approach called DIffusion-guided DIversity (DIDI) for offline behavioral generation. The goal of DIDI is to learn a diverse set of skills from a mixture of label-free offline data. We achieve this by leveraging diffusion probabilistic models as priors to guide the learning process and regularize the policy. By optimizing a joint objective that incorporates diversity and diffusion-guided regularization, we encourage the emergence of diverse behaviors while maintaining the similarity to the offline data. Experimental results in four decision-making domains (Push, Kitchen, Humanoid, and D4RL tasks) show that DIDI is effective in discovering diverse and discriminative skills. We also introduce skill stitching and skill interpolation, which highlight the generalist nature of the learned skill space. Further, by incorporating an extrinsic reward function, DIDI enables reward-guided behavior generation, facilitating the learning of diverse and optimal behaviors from sub-optimal data.
APA
Liu, J., Guo, X., Zhuang, Z. & Wang, D.. (2024). DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:31032-31047 Available from https://proceedings.mlr.press/v235/liu24s.html.

Related Material