# Real-World Reinforcement Learning with MPC Scaffolding for Dexterous Manipulation

arXiv: https://arxiv.org/abs/2609.14878 · HTML: https://mlsanity.com/paper/2609.14878/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 28 of its 32 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 28 of 28)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [AWAC: Accelerating Online Reinforcement Learning with Offline Datasets](https://mlsanity.com/paper/2006.09359/) (2020)
- [Efficient Online Reinforcement Learning with Offline Data](https://mlsanity.com/paper/2302.02948/) (2023)
- [Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble](https://mlsanity.com/paper/2107.00591/) (2021)
- [Deep Dynamics Models for Learning Dexterous Manipulation](https://mlsanity.com/paper/1909.11652/) (2019)
- [Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning](https://mlsanity.com/paper/2410.21845/) (2024)
- [DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality](https://mlsanity.com/paper/2210.13702/) (2022)
- [Expressive Whole-Body Control for Humanoid Robots](https://mlsanity.com/paper/2402.16796/) (2024)
- [SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning](https://mlsanity.com/paper/2401.16013/) (2024)
- [In-Hand Object Rotation via Rapid Motor Adaptation](https://mlsanity.com/paper/2210.04887/) (2022)
- [Jump-Start Reinforcement Learning](https://mlsanity.com/paper/2204.02372/) (2022)
- [Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes](https://mlsanity.com/paper/2211.11744/) (2022)
- [From One Hand to Multiple Hands: Imitation Learning for Dexterous Manipulation from Single-Camera Teleoperation](https://mlsanity.com/paper/2204.12490/) (2022)
- [Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone](https://mlsanity.com/paper/2412.06685/) (2024)
- [DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation](https://mlsanity.com/paper/2505.21864/) (2025)
- [RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning](https://mlsanity.com/paper/2510.14830/) (2025)
- [Residual Off-Policy RL for Finetuning Behavior Cloning Policies](https://mlsanity.com/paper/2509.19301/) (2025)
- [Learning Dexterous Manipulation Policies from Experience and Imitation](https://mlsanity.com/paper/1611.05095/) (2016)
- [Sampling-based Exploration for Reinforcement Learning of Dexterous Manipulation](https://mlsanity.com/paper/2303.03486/) (2023)
- [SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation](https://mlsanity.com/paper/2602.16863/) (2026)
- [DROP: Dexterous Reorientation via Online Planning](https://mlsanity.com/paper/2409.14562/) (2024)
- [Accelerating and Scaling MPC-Guided Reinforcement Learning for Humanoid Locomotion and Manipulation](https://mlsanity.com/paper/2606.05687/) (2026)
- [Sampling-Based Model Predictive Control for Dexterous Manipulation on a Biomimetic Tendon-Driven Hand](https://mlsanity.com/paper/2411.06183/) (2024)

## Built on by (most cited first, 1 of 1)

- [Action Shaping: Policies Absorb What They Can Express](https://mlsanity.com/paper/2609.32752/) (2026)

## Abstract (arXiv)

Real-world reinforcement learning (RL) offers a promising route to dexterous manipulation policies that can adapt directly from physical interaction, but learning is hindered by inefficient early exploration and costly failures. We propose a framework that uses sampling-based model predictive control (MPC) as scaffolding for real-world dexterous RL, providing structured prior experience and task-directed guidance during learning without human demonstrations or corrective actions. A small set of MPC trajectories is first used to populate an offline replay buffer and to pretrain the actor and critic. During online learning, MPC intermittently guides data collection while an off-policy Soft Actor-Critic learner trains from both prior MPC experience and newly collected physical interaction, with control gradually transitioning to the learned policy. On continuous in-hand rotation with a 16-DoF Allegro hand, initialized from 20 MPC trajectories collected in 12 minutes on hardware, the policy reaches 100% success after 7 minutes of online RL, with about three object drops on average during training. After 20 minutes of online learning, the policy achieves more than five times the rotation speed of the MPC controller and completes 1000 consecutive rotations without a drop. Ablations show complementary benefits from MPC-based pretraining, retained MPC experience, and online MPC guidance, while additional experiments demonstrate rapid adaptation to new object geometries and successful goal-conditioned reorientation.