Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hong, Matthew M., Zhang, Jesse, Nagabandi, Anusha, Gupta, Abhishek
Format:	Preprint
Published:	2026
Subjects:	Robotics Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning
by: Wagenmaker, Andrew, et al.
Published: (2025)

Residual Off-Policy RL for Finetuning Behavior Cloning Policies
by: Ankile, Lars, et al.
Published: (2025)

Steering Your Diffusion Policy with Latent Space Reinforcement Learning
by: Wagenmaker, Andrew, et al.
Published: (2025)

Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets
by: Zhu, Chuning, et al.
Published: (2025)

PEEK: Guiding and Minimal Image Representations for Zero-Shot Generalization of Robot Manipulation Policies
by: Zhang, Jesse, et al.
Published: (2025)

Efficient Evaluation of Multi-Task Robot Policies With Active Experiment Selection
by: Anwar, Abrar, et al.
Published: (2025)

Confidence-Controlled Exploration: Efficient Sparse-Reward Policy Learning for Robot Navigation
by: Patel, Bhrij, et al.
Published: (2023)

Policy-Guided Diffusion
by: Jackson, Matthew Thomas, et al.
Published: (2024)

Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation
by: Levy, Jacob, et al.
Published: (2026)

SOE: Sample-Efficient Robot Policy Self-Improvement via On-Manifold Exploration
by: Jin, Yang, et al.
Published: (2025)

Diffusion Augmented Agents: A Framework for Efficient Exploration and Transfer Learning
by: Di Palo, Norman, et al.
Published: (2024)

TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models
by: Liu, Zuxin, et al.
Published: (2023)

EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Data
by: Zhang, Jesse, et al.
Published: (2024)

Latent Policy Steering with Embodiment-Agnostic Pretrained World Models
by: Wang, Yiqi, et al.
Published: (2025)

Safe Exploration via Policy Priors
by: Wendl, Manuel, et al.
Published: (2026)

Deep Active Inference with Diffusion Policy and Multiple Timescale World Model for Real-World Exploration and Navigation
by: Yokozawa, Riko, et al.
Published: (2025)

Unsupervised Learning of Efficient Exploration: Pre-training Adaptive Policies via Self-Imposed Goals
by: Pappalardo, Octavio
Published: (2026)

SPRINT: Scalable Policy Pre-Training via Language Instruction Relabeling
by: Zhang, Jesse, et al.
Published: (2023)

OGPO: Sample Efficient Full-Finetuning of Generative Control Policies
by: Patil, Sarvesh, et al.
Published: (2026)

SIME: Enhancing Policy Self-Improvement with Modal-level Exploration
by: Jin, Yang, et al.
Published: (2025)

VAMOS: A Hierarchical Vision-Language-Action Model for Capability-Modulated and Steerable Navigation
by: Castro, Mateo Guaman, et al.
Published: (2025)

Evolutionary Policy Optimization
by: Wang, Jianren, et al.
Published: (2025)

Diffusion Policies with Value-Conditional Optimization for Offline Reinforcement Learning
by: Ma, Yunchang, et al.
Published: (2025)

Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation
by: Xue, Han, et al.
Published: (2025)

Fine-tuning Diffusion Policies with Backpropagation Through Diffusion Timesteps
by: Yang, Ningyuan, et al.
Published: (2025)

Variational Distillation of Diffusion Policies into Mixture of Experts
by: Zhou, Hongyi, et al.
Published: (2024)

Adaptive Diffusion Policy Optimization for Robotic Manipulation
by: Jiang, Huiyun, et al.
Published: (2025)

ESCORT: Efficient Stein-variational and Sliced Consistency-Optimized Temporal Belief Representation for POMDPs
by: Zhang, Yunuo, et al.
Published: (2025)

TopSpark: A Timestep Optimization Methodology for Energy-Efficient Spiking Neural Networks on Autonomous Mobile Agents
by: Putra, Rachmad Vidya Wicaksana, et al.
Published: (2023)

Force-Modulated Visual Policy for Robot-Assisted Dressing with Arm Motions
by: Hao, Alexis Yihong, et al.
Published: (2025)

CoFineLLM: Conformal Finetuning of LLMs for Language-Instructed Robot Planning
by: Wang, Jun, et al.
Published: (2025)

SPAARS: Safer RL Policy Alignment through Abstract Exploration and Refined Exploitation of Action Space
by: K, Swaminathan S, et al.
Published: (2026)

Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
by: Zheng, Ruijie, et al.
Published: (2024)

REFINE-DP: Diffusion Policy Fine-tuning for Humanoid Loco-manipulation via Reinforcement Learning
by: Gu, Zhaoyuan, et al.
Published: (2026)

Semantic World Models
by: Berg, Jacob, et al.
Published: (2025)

Robust Policy Learning via Offline Skill Diffusion
by: Kim, Woo Kyung, et al.
Published: (2024)

WARPD: World model Assisted Reactive Policy Diffusion
by: Hegde, Shashank, et al.
Published: (2024)

Efficient Preference-Based Reinforcement Learning: Randomized Exploration Meets Experimental Design
by: Schlaginhaufen, Andreas, et al.
Published: (2025)

In-Context Policy Adaptation via Cross-Domain Skill Diffusion
by: Yoo, Minjong, et al.
Published: (2025)

Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient
by: Wang, Wenlong, et al.
Published: (2024)