# Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation

arXiv: https://arxiv.org/abs/2105.14829 · HTML: https://mlsanity.com/paper/2105.14829/

## Key facts

- Cited by 85 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 54 references that are in the map.
- First posted on arXiv 31 May 2021.

## Builds on (most cited first, 30 of 41)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/1806.10293/) (2018)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019)
- [Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels](https://mlsanity.com/paper/2004.13649/) (2020)
- [Learning agile and dynamic motor skills for legged robots](https://mlsanity.com/paper/1901.08652/) (2019)
- [DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion](https://mlsanity.com/paper/1901.04780/) (2019)
- [Transporter Networks: Rearranging the Visual World for Robotic Manipulation](https://mlsanity.com/paper/2010.14406/) (2020)
- [Overcoming Exploration in Reinforcement Learning with Demonstrations](https://mlsanity.com/paper/1709.10089/) (2017)
- [Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards](https://mlsanity.com/paper/1707.08817/) (2017)
- [Deep Visual Foresight for Planning Robot Motion](https://mlsanity.com/paper/1610.00696/) (2016)
- [Improving Sample Efficiency in Model-Free Reinforcement Learning from Images](https://mlsanity.com/paper/1910.01741/) (2019)
- [Asymmetric Actor Critic for Image-Based Robot Learning](https://mlsanity.com/paper/1710.06542/) (2017)
- [CAD2RL: Real Single-Image Flight without a Single Real Image](https://mlsanity.com/paper/1611.04201/) (2016)
- [Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning](https://mlsanity.com/paper/1809.02925/) (2018)
- [Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks](https://mlsanity.com/paper/1812.07252/) (2018)
- [Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks](https://mlsanity.com/paper/1810.10191/) (2018)
- [TossingBot: Learning to Throw Arbitrary Objects with Residual Physics](https://mlsanity.com/paper/1903.11239/) (2019)
- [Sim-to-Real Reinforcement Learning for Deformable Object Manipulation](https://mlsanity.com/paper/1806.07851/) (2018)

## Built on by (most cited first, 30 of 85)

- [Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation](https://mlsanity.com/paper/2209.05451/) (2022)
- [DayDreamer: World Models for Physical Robot Learning](https://mlsanity.com/paper/2206.14176/) (2022)
- [3D Diffuser Actor: Policy Diffusion with 3D Scene Representations](https://mlsanity.com/paper/2402.10885/) (2024)
- [Real-World Robot Learning with Masked Visual Pre-training](https://mlsanity.com/paper/2210.03109/) (2022)
- [Masked World Models for Visual Control](https://mlsanity.com/paper/2206.14244/) (2022)
- [Language-Driven Representation Learning for Robotics](https://mlsanity.com/paper/2302.12766/) (2023)
- [Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation](https://mlsanity.com/paper/2403.03949/) (2024)
- [Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation](https://mlsanity.com/paper/2306.17817/) (2023)
- [THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation](https://mlsanity.com/paper/2402.08191/) (2024)
- [Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation](https://mlsanity.com/paper/2106.12534/) (2021)
- [Instruction-driven history-aware policies for robotic manipulations](https://mlsanity.com/paper/2209.04899/) (2022)
- [Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation](https://mlsanity.com/paper/2403.03890/) (2024)
- [From Imitation to Refinement -- Residual RL for Precise Assembly](https://mlsanity.com/paper/2407.16677/) (2024)
- [Multi-View Masked World Models for Visual Robotic Manipulation](https://mlsanity.com/paper/2302.02408/) (2023)
- [Data Quality in Imitation Learning](https://mlsanity.com/paper/2306.02437/) (2023)
- [Auto-Lambda: Disentangling Dynamic Task Relationships](https://mlsanity.com/paper/2202.03091/) (2022)
- [Waypoint-Based Imitation Learning for Robotic Manipulation](https://mlsanity.com/paper/2307.14326/) (2023)
- [Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasets](https://mlsanity.com/paper/2304.08742/) (2023)
- [PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation](https://mlsanity.com/paper/2309.15596/) (2023)
- [Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks](https://mlsanity.com/paper/2405.01534/) (2024)
- [RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning](https://mlsanity.com/paper/2409.14674/) (2024)
- [ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning](https://mlsanity.com/paper/2505.07395/) (2025)
- [KITE: Keypoint-Conditioned Policies for Semantic Manipulation](https://mlsanity.com/paper/2306.16605/) (2023)
- [Run-time Observation Interventions Make Vision-Language-Action Models More Visually Robust](https://mlsanity.com/paper/2410.01971/) (2024)
- [Exploring the Limits of Vision-Language-Action Manipulations in Cross-task Generalization](https://mlsanity.com/paper/2505.15660/) (2025)
- [Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point Clouds](https://mlsanity.com/paper/2210.07442/) (2022)
- [BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark](https://mlsanity.com/paper/2407.07788/) (2024)
- [DexPBT: Scaling up Dexterous Manipulation for Hand-Arm Systems with Population Based Training](https://mlsanity.com/paper/2305.12127/) (2023)
- [Shelving, Stacking, Hanging: Relational Pose Diffusion for Multi-modal Rearrangement](https://mlsanity.com/paper/2307.04751/) (2023)
- [In-Context Learning Enables Robot Action Prediction in LLMs](https://mlsanity.com/paper/2410.12782/) (2024)

## Abstract (arXiv)

Despite the success of reinforcement learning methods, they have yet to have their breakthrough moment when applied to a broad range of robotic manipulation tasks. This is partly due to the fact that reinforcement learning algorithms are notoriously difficult and time consuming to train, which is exacerbated when training from images rather than full-state inputs. As humans perform manipulation tasks, our eyes closely monitor every step of the process with our gaze focusing sequentially on the objects being manipulated. With this in mind, we present our Attention-driven Robotic Manipulation (ARM) algorithm, which is a general manipulation algorithm that can be applied to a range of sparse-rewarded tasks, given only a small number of demonstrations. ARM splits the complex task of manipulation into a 3 stage pipeline: (1) a Q-attention agent extracts relevant pixel locations from RGB and point cloud inputs, (2) a next-best pose agent that accepts crops from the Q-attention agent and outputs poses, and (3) a control agent that takes the goal pose and outputs joint actions. We show that current learning algorithms fail on a range of RLBench tasks, whilst ARM is successful.