# Task-Oriented Grasping Using Reinforcement Learning with a Contextual Reward Machine

arXiv: https://arxiv.org/abs/2512.10235 · HTML: https://mlsanity.com/paper/2512.10235/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 11 of its 35 references that are in the map.
- First posted on arXiv 11 Dec 2025.

## 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, 11 of 11)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects](https://mlsanity.com/paper/2312.08344/) (2023)
- [Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning](https://mlsanity.com/paper/2010.03950/) (2020)
- [DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation](https://mlsanity.com/paper/2210.02697/) (2022)
- [DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Video](https://mlsanity.com/paper/2202.00164/) (2022)
- [Learning Dexterous Grasping with Object-Centric Visual Affordances](https://mlsanity.com/paper/2009.01439/) (2020)
- [DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation](https://mlsanity.com/paper/2211.09423/) (2022)
- [AffordPose: A Large-scale Dataset of Hand-Object Interactions with Affordance-driven Hand Pose](https://mlsanity.com/paper/2309.08942/) (2023)
- [Target Search and Navigation in Heterogeneous Robot Systems with Deep Reinforcement Learning](https://mlsanity.com/paper/2308.00331/) (2023)
- [A Deep Reinforcement Learning Architecture for Multi-stage Optimal Control](https://mlsanity.com/paper/1911.10684/) (2019)

## Abstract (arXiv)

This paper presents a reinforcement learning framework that incorporates a Contextual Reward Machine for task-oriented grasping. The Contextual Reward Machine reduces task complexity by decomposing grasping tasks into manageable sub-tasks. Each sub-task is associated with a stage-specific context, including a reward function, an action space, and a state abstraction function. This contextual information enables efficient intra-stage guidance and improves learning efficiency by reducing the state-action space and guiding exploration within clearly defined boundaries. In addition, transition rewards are introduced to encourage or penalize transitions between stages which guides the model toward desirable stage sequences and further accelerates convergence. When integrated with the Proximal Policy Optimization algorithm, the proposed method achieved a 95% success rate across 1,000 simulated grasping tasks encompassing diverse objects, affordances, and grasp topologies. It outperformed the state-of-the-art methods in both learning speed and success rate. The approach was transferred to a real robot, where it achieved a success rate of 83.3% in 60 grasping tasks over six affordances. These experimental results demonstrate superior accuracy, data efficiency, and learning efficiency. They underscore the model's potential to advance task-oriented grasping in both simulated and real-world settings.