Enhancing Decision Transformer with Diffusion-Based Trajectory Branch Generation

TL;DR

This paper introduces Diffusion-Based Trajectory Branch Generation to enhance Decision Transformer by expanding trajectories with diffusion-generated branches, enabling better policy learning and outperforming state-of-the-art methods on benchmarks.

Contribution

It proposes a novel diffusion-based method to expand offline RL datasets with trajectory branches, improving policy learning without modifying existing models.

Findings

DT with BG outperforms state-of-the-art methods on D4RL benchmarks.

Trajectory expansion with diffusion improves policy convergence.

The method effectively prevents convergence to sub-optimal trajectories.

Abstract

Decision Transformer (DT) can learn effective policy from offline datasets by converting the offline reinforcement learning (RL) into a supervised sequence modeling task, where the trajectory elements are generated auto-regressively conditioned on the return-to-go (RTG).However, the sequence modeling learning approach tends to learn policies that converge on the sub-optimal trajectories within the dataset, for lack of bridging data to move to better trajectories, even if the condition is set to the highest RTG.To address this issue, we introduce Diffusion-Based Trajectory Branch Generation (BG), which expands the trajectories of the dataset with branches generated by a diffusion model.The trajectory branch is generated based on the segment of the trajectory within the dataset, and leads to trajectories with higher returns.We concatenate the generated branch with the trajectory segment as an expansion of the trajectory.After expanding, DT has more opportunities to learn policies to move to better trajectories, preventing it from converging to the sub-optimal trajectories.Empirically, after processing with BG, DT outperforms state-of-the-art sequence modeling methods on D4RL benchmark, demonstrating the effectiveness of adding branches to the dataset without further modifications.