# ADEPT: Accelerating Dexterity via Pre-Training and Post-Training using Reinforcement Learning

arXiv: https://arxiv.org/abs/2608.19182 · HTML: https://mlsanity.com/paper/2608.19182/

## Key facts

- Cited by 2 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 32 of its 36 references that are in the map.
- First posted on arXiv 19 Aug 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, 30 of 32)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Solving Rubik's Cube with a Robot Hand](https://mlsanity.com/paper/1910.07113/) (2019)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [Population Based Training of Neural Networks](https://mlsanity.com/paper/1711.09846/) (2017)
- [Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning](https://mlsanity.com/paper/2303.05479/) (2023)
- [RL's Razor: Why Online Reinforcement Learning Forgets Less](https://mlsanity.com/paper/2509.04259/) (2025)
- [A System for General In-Hand Object Re-Orientation](https://mlsanity.com/paper/2111.03043/) (2021)
- [DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality](https://mlsanity.com/paper/2210.13702/) (2022)
- [URLB: Unsupervised Reinforcement Learning Benchmark](https://mlsanity.com/paper/2110.15191/) (2021)
- [In-Hand Object Rotation via Rapid Motor Adaptation](https://mlsanity.com/paper/2210.04887/) (2022)
- [Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes](https://mlsanity.com/paper/2211.11744/) (2022)
- [General In-Hand Object Rotation with Vision and Touch](https://mlsanity.com/paper/2309.09979/) (2023)
- [FMB: a Functional Manipulation Benchmark for Generalizable Robotic Learning](https://mlsanity.com/paper/2401.08553/) (2024)
- [Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data](https://mlsanity.com/paper/2412.07762/) (2024)
- [Riemannian Motion Policies](https://mlsanity.com/paper/1801.02854/) (2018)
- [DextrAH-RGB: Visuomotor Policies to Grasp Anything with Dexterous Hands](https://mlsanity.com/paper/2412.01791/) (2024)
- [DextrAH-G: Pixels-to-Action Dexterous Arm-Hand Grasping with Geometric Fabrics](https://mlsanity.com/paper/2407.02274/) (2024)
- [Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning](https://mlsanity.com/paper/2210.13846/) (2022)
- [DexPBT: Scaling up Dexterous Manipulation for Hand-Arm Systems with Population Based Training](https://mlsanity.com/paper/2305.12127/) (2023)
- [Local Policies Enable Zero-shot Long-horizon Manipulation](https://mlsanity.com/paper/2410.22332/) (2024)
- [RMPflow: A Computational Graph for Automatic Motion Policy Generation](https://mlsanity.com/paper/1811.07049/) (2018)
- [SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation](https://mlsanity.com/paper/2602.16863/) (2026)
- [DemoStart: Demonstration-led auto-curriculum applied to sim-to-real with multi-fingered robots](https://mlsanity.com/paper/2409.06613/) (2024)
- [Emergent Dexterity via Diverse Resets and Large-Scale Reinforcement Learning](https://mlsanity.com/paper/2603.15789/) (2026)
- [Spatially anchored Tactile Awareness for Robust Dexterous Manipulation](https://mlsanity.com/paper/2510.14647/) (2025)
- [Tacmap: Bridging the Tactile Sim-to-Real Gap via Geometry-Consistent Penetration Depth Map](https://mlsanity.com/paper/2602.21625/) (2026)
- [Optimization Fabrics](https://mlsanity.com/paper/2008.02399/) (2020)
- [Geometric Fabrics: a Safe Guiding Medium for Policy Learning](https://mlsanity.com/paper/2405.02250/) (2024)

## Built on by (most cited first, 2 of 2)

- [WeaveRL: Weaving Reconstruction into Scene-Aware Fabrics for Perceptive Reinforcement Learning](https://mlsanity.com/paper/2609.18685/) (2026)
- [EigenDEXplore: Structured Exploration for Dexterous Manipulation with Human Priors](https://mlsanity.com/paper/2610.07681/) (2026)

## Abstract (arXiv)

We introduce Accelerating Dexterity via Pre-Training (ADEPT), a large-scale reinforcement learning (RL) framework for learning sim-to-real transferable dexterity across high degree-of-freedom (DoF) robot embodiments that can solve long-horizon tasks directly from raw visuo-tactile perception. ADEPT pretrains a dexterous policy on a generic object reposing task, then post-trains downstream policies with this pretrained behavior as a prior. ADEPT enables learning new behaviors that are otherwise difficult to discover from scratch on multi-fingered robots and avoids learning the same set of skills over again for every new downstream task. The pretrained policy zero-shots the reposing phase of downstream tasks, but na"ive RL fine-tuning rapidly degrades this capability during transfer. We address this with a stable post-training recipe combining behavior-cloning distillation, critic warm-up, and conservative on-policy updates. To safely exploit the full kinematic dexterity, we introduce a joint-space Geometric Fabric that mediates between the RL policy and the robot. We distill post-trained teachers into perceptive students that zero-shot sim-to-real transfer on two embodiments: a 23 DoF Kuka-Allegro with two RGB cameras, and a 29 DoF Flexiv-Sharpa with two RGB cameras and five vision-based tactile sensors, and can solve long-horizon tasks from challenging initial states with dexterity at human-level speed.