Skip to yearly menu bar Skip to main content


Generating Behaviorally Diverse Policies with Latent Diffusion Models

Shashank Hegde · Sumeet Batra · K.R. Zentner · Gaurav Sukhatme

Great Hall & Hall B1+B2 (level 1) #531


Recent progress in Quality Diversity Reinforcement Learning (QD-RL) has enabled learning a collection of behaviorally diverse, high performing policies. However, these methods typically involve storing thousands of policies, which results in high space-complexity and poor scaling to additional behaviors. Condensing the archive into a single model while retaining the performance and coverage of theoriginal collection of policies has proved challenging. In this work, we propose using diffusion models to distill the archive into a single generative model over policy parameters. We show that our method achieves a compression ratio of 13x while recovering 98% of the original rewards and 89% of the original humanoid archive coverage. Further, the conditioning mechanism of diffusion models allowsfor flexibly selecting and sequencing behaviors, including using language. Project website:

Chat is not available.