TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning

TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning

Matthew M. Hong, Jesse Zhang, Anusha Nagabandi, Abhishek Gupta · · 2026

Framework

N/A

License

N/A

Stars

0

Summary

Fine-tuning pre-trained robot policies with reinforcement learning (RL) often inherits the bottlenecks introduced by pre-training with behavioral cloning (BC), which produces narrow action distributions that lack the coverage necessary for...

Abstract Summary

Fine-tuning pre-trained robot policies with reinforcement learning (RL) often inherits the bottlenecks introduced by pre-training with behavioral cloning (BC), which produces narrow action distributions that lack the coverage necessary for downstream exploration. We present a unified framework that enables the exploration necessary to enable efficient robot policy finetuning by bridging BC pre-training and RL fine-tuning. Our pre-training method, Context-Smoothed Pre-training (CSP), injects forward-diffusion noise into policy inputs, creating a continuum between precise imitation and broad action coverage. We then fine-tune pre-trained policies via Timestep-Modulated Reinforcement Learning (TMRL), which trains the agent to dynamically adjust this conditioning during fine-tuning by modulating the diffusion timestep, granting explicit control over exploration. Integrating seamlessly with arbitrary policy inputs, e.g., states, 3D point clouds, or image-based VLA policies, we show that TMRL improves RL fine-tuning sample efficiency. Notably, TMRL enables successful real-world fine-tuning on complex manipulation tasks in under one hour. Videos and code available at https://weirdlabuw.github.io/tmrl/.

Key Points

  • Introduces TMRL, advancing rl research.
  • Detailed evaluation demonstrates effectiveness on benchmarks and real-world scenarios.
  • Provides insights into methodology and architectural choices.

Abstract

Fine-tuning pre-trained robot policies with reinforcement learning (RL) often inherits the bottlenecks introduced by pre-training with behavioral cloning (BC), which produces narrow action distributions that lack the coverage necessary for downstream exploration. We present a unified framework that enables the exploration necessary to enable efficient robot policy finetuning by bridging BC pre-training and RL fine-tuning. Our pre-training method, Context-Smoothed Pre-training (CSP), injects forward-diffusion noise into policy inputs, creating a continuum between precise imitation and broad action coverage. We then fine-tune pre-trained policies via Timestep-Modulated Reinforcement Learning (TMRL), which trains the agent to dynamically adjust this conditioning during fine-tuning by modulating the diffusion timestep, granting explicit control over exploration. Integrating seamlessly with arbitrary policy inputs, e.g., states, 3D point clouds, or image-based VLA policies, we show that TMRL improves RL fine-tuning sample efficiency. Notably, TMRL enables successful real-world fine-tuning on complex manipulation tasks in under one hour. Videos and code available at https://weirdlabuw.github.io/tmrl/.

Share

Related Papers

LeRobot: A Library for Real-World Robot Learning

LeRobot: A Library for Real-World Robot Learning

Remi Cadene, Simon Alibert, Alexander Soare et al. · NeurIPS 2024 Workshop · Jun 2024

Hugging Face's LeRobot is an open-source PyTorch framework providing pretrained models, datasets, and training scripts for imitation and reinforcement learning on real robots, lowering the entry barrier to robot learning.

imitation-learning rl foundation-models manipulation
Code PDF Beginner
GitHub ★ 24,333 Code updated: May 2026
EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from a Monocular Egocentric Camera

EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from a Monocular Egocentric Camera

Christen Millerdurai, Shaoxiang Wang, Yaxu Xie et al. · SIGGRAPH 2026 · May 2026

Reconstructing the absolute 3D pose and shape of the hands from the user's viewpoint using a single head-mounted camera is crucial for practical egocentric interaction in AR/VR, telepresence, and hand-centric manipulation tasks, where sensing must...

manipulation manipulation simulation
Code PDF Intermediate
Code ★ 0 May 2026
Aligning Flow Map Policies with Optimal Q-Guidance

Aligning Flow Map Policies with Optimal Q-Guidance

Christos Ziakas, Alessandra Russo, Avishek Joey Bose · arXiv · May 2026

Generative policies based on expressive model classes, such as diffusion-models and flow matching, are well-suited to complex control problems with highly multimodal action distributions. Their expressivity, however, comes at a significant inference cost:...

rl diffusion-models manipulation
PDF Advanced
No code repo May 2026