Cover Image

Steering Your Diffusion Policy with Latent Space Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wagenmaker, Andrew, Nakamoto, Mitsuhiko, Zhang, Yunchu, Park, Seohong, Yagoub, Waleed, Nagabandi, Anusha, Gupta, Abhishek, Levine, Sergey
Format:	Preprint
Published:	2025
Subjects:	Robotics Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance
by: Nakamoto, Mitsuhiko, et al.
Published: (2024)

RFS: Reinforcement Learning with Residual Flow Steering for Dexterous Manipulation
by: Su, Entong, et al.
Published: (2026)

TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning
by: Hong, Matthew M., et al.
Published: (2026)

Foundation Policies with Hilbert Representations
by: Park, Seohong, et al.
Published: (2024)

Behavioral Exploration: Learning to Explore via In-Context Adaptation
by: Wagenmaker, Andrew, et al.
Published: (2025)

HIQL: Offline Goal-Conditioned RL with Latent States as Actions
by: Park, Seohong, et al.
Published: (2023)

METRA: Scalable Unsupervised RL with Metric-Aware Abstraction
by: Park, Seohong, et al.
Published: (2023)

Decoupled Q-Chunking
by: Li, Qiyang, et al.
Published: (2025)

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)

Unsupervised-to-Online Reinforcement Learning
by: Kim, Junsu, et al.
Published: (2024)

Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL
by: Wagenmaker, Andrew, et al.
Published: (2024)

Robust Finetuning of Vision-Language-Action Robot Policies via Parameter Merging
by: Yadav, Yajat, et al.
Published: (2025)

Diffusion Guidance Is a Controllable Policy Improvement Operator
by: Frans, Kevin, et al.
Published: (2025)

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

ASID: Active Exploration for System Identification in Robotic Manipulation
by: Memmel, Marius, et al.
Published: (2024)

Latent-Conditioned Policy Gradient for Multi-Objective Deep Reinforcement Learning
by: Kanazawa, Takuya, et al.
Published: (2023)

RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning
by: Xu, Charles, et al.
Published: (2024)

Flow Q-Learning
by: Park, Seohong, et al.
Published: (2025)

Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings
by: Frans, Kevin, et al.
Published: (2024)

Symmetry-Aware Steering of Equivariant Diffusion Policies: Benefits and Limits
by: Park, Minwoo, et al.
Published: (2025)

ATK: Automatic Task-driven Keypoint Selection for Robust Policy Learning
by: Zhang, Yunchu, et al.
Published: (2025)

Latent Policy Steering through One-Step Flow Policies
by: Im, Hokyun, et al.
Published: (2026)

Reinforcement Learning with Action Chunking
by: Li, Qiyang, et al.
Published: (2025)

Multistep Quasimetric Learning for Scalable Goal-conditioned Reinforcement Learning
by: Zheng, Bill Chunyuan, et al.
Published: (2025)

RoboReward: General-Purpose Vision-Language Reward Models for Robotics
by: Lee, Tony, et al.
Published: (2026)

Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learning
by: Huang, Kevin, et al.
Published: (2025)

CCIL: Continuity-based Data Augmentation for Corrective Imitation Learning
by: Ke, Liyiming, et al.
Published: (2023)

Dual Goal Representations
by: Park, Seohong, et al.
Published: (2025)

Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation
by: Doshi, Ria, et al.
Published: (2024)

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment
by: Wu, Yilin, et al.
Published: (2025)

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

Transitive RL: Value Learning via Divide and Conquer
by: Park, Seohong, et al.
Published: (2025)

Is Value Learning Really the Main Bottleneck in Offline RL?
by: Park, Seohong, et al.
Published: (2024)

PolaRiS: Scalable Real-to-Sim Evaluations for Generalist Robot Policies
by: Jain, Arhan, et al.
Published: (2025)

Real-Time Execution of Action Chunking Flow Policies
by: Black, Kevin, et al.
Published: (2025)

Scalable Offline Model-Based RL with Action Chunks
by: Park, Kwanyoung, et al.
Published: (2025)

When to Act, Ask, or Learn: Uncertainty-Aware Policy Steering
by: Yuan, Jessie, et al.
Published: (2026)

Policy Adaptation via Language Optimization: Decomposing Tasks for Few-Shot Imitation
by: Myers, Vivek, et al.
Published: (2024)

Grammarization-Based Grasping with Deep Multi-Autoencoder Latent Space Exploration by Reinforcement Learning Agent
by: Askianakis, Leonidas
Published: (2024)