Is Conditional Generative Modeling all you need for Decision-Making?

TL;DR

This paper explores using conditional generative models, specifically diffusion models, for decision-making, showing they can outperform traditional offline RL methods and handle multiple constraints and skills.

Contribution

It introduces a novel approach of modeling policies as return-conditional diffusion models, simplifying decision-making and enabling multi-constraint and skill composition capabilities.

Findings

Outperforms existing offline RL approaches on standard benchmarks.

Models can satisfy multiple constraints simultaneously.

Demonstrates skill composition through conditional diffusion models.

Abstract

Recent improvements in conditional generative modeling have made it possible to generate high-quality images from language descriptions alone. We investigate whether these methods can directly address the problem of sequential decision-making. We view decision-making not through the lens of reinforcement learning (RL), but rather through conditional generative modeling. To our surprise, we find that our formulation leads to policies that can outperform existing offline RL approaches across standard benchmarks. By modeling a policy as a return-conditional diffusion model, we illustrate how we may circumvent the need for dynamic programming and subsequently eliminate many of the complexities that come with traditional offline RL. We further demonstrate the advantages of modeling policies as conditional diffusion models by considering two other conditioning variables: constraints and skills. Conditioning on a single constraint or skill during training leads to behaviors at test-time that can satisfy several constraints together or demonstrate a composition of skills. Our results illustrate that conditional generative modeling is a powerful tool for decision-making.