Consistency Trajectory Planning: High-Quality and Efficient Trajectory Optimization for Offline Model-Based Reinforcement Learning

TL;DR

This paper presents Consistency Trajectory Planning (CTP), a new offline reinforcement learning method that enables fast, high-quality trajectory optimization using a single-step diffusion-based approach, significantly reducing inference time.

Contribution

The paper introduces CTP, a novel offline model-based RL technique that achieves efficient, single-step trajectory optimization with high performance, outperforming existing diffusion-based planning methods.

Findings

CTP outperforms existing diffusion-based planning methods on D4RL benchmarks.

CTP achieves over 120x speedup in inference time compared to prior diffusion methods.

CTP maintains high policy quality with significantly fewer denoising steps.

Abstract

This paper introduces Consistency Trajectory Planning (CTP), a novel offline model-based reinforcement learning method that leverages the recently proposed Consistency Trajectory Model (CTM) for efficient trajectory optimization. While prior work applying diffusion models to planning has demonstrated strong performance, it often suffers from high computational costs due to iterative sampling procedures. CTP supports fast, single-step trajectory generation without significant degradation in policy quality. We evaluate CTP on the D4RL benchmark and show that it consistently outperforms existing diffusion-based planning methods in long-horizon, goal-conditioned tasks. Notably, CTP achieves higher normalized returns while using significantly fewer denoising steps. In particular, CTP achieves comparable performance with over $120\times$ speedup in inference time, demonstrating its practicality and effectiveness for high-performance, low-latency offline planning.