mlsanityData to 14 Oct 2026

Coarse-to-fine Q-attention with Tree Expansion

arXiv 2204.12471 ↗First posted 26 Apr 2022cs.RO cs.AI cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Coarse-to-fine Q-attention enables sample-efficient robot manipulation by discretizing the translation space in a coarse-to-fine manner, where the resolution gradually increases at each layer in the hierarchy. Although effective, Q-attention suffers from "coarse ambiguity" - when voxelization is significantly coarse, it is not feasible to distinguish similar-looking objects without first inspecting at a finer resolution. To combat this, we propose to envision Q-attention as a tree that can be expanded and used to accumulate value estimates across the top-k voxels at each Q-attention depth. When our extension, Q-attention with Tree Expansion (QTE), replaces standard Q-attention in the Attention-driven Robot Manipulation (ARM) system, we are able to accomplish a larger set of tasks; especially on those that suffer from "coarse ambiguity". In addition to evaluating our approach across 12 RLBench tasks, we also show that the improved performance is visible in a real-world task involving small objects.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 23 of its 32 references that are in the map. First posted on arXiv 26 Apr 2022.

Builds on

23 of 32 references.

References · 23

  1. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 743
  2. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 689
  3. 2020Transporter Networks: Rearranging the Visual World for Robotic Manipulationcited by 344
  4. 2017Asymmetric Actor Critic for Image-Based Robot Learningcited by 238
  5. 2018Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networkscited by 174
  6. 2018Sim-to-Real Reinforcement Learning for Deformable Object Manipulationcited by 131
  7. 2018Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learningcited by 128
  8. 2021Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisationcited by 122
  9. 2018Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approachcited by 120
  10. 2019Grasping in the Wild:Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrationscited by 107
  11. 2021Volumetric Grasping Network: Real-time 6 DOF Grasp Detection in Cluttercited by 95
  12. 2021Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulationcited by 85
11 more
  1. 2018Composable Deep Reinforcement Learning for Robotic Manipulationcited by 72
  2. 2020MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusioncited by 46
  3. 2019Monte-Carlo Tree Search for Efficient Visually Guided Rearrangement Planningcited by 24
  4. 20163D Simulation for Robot Arm Control with Deep Q-Learningcited by 21
  5. 2021Visual Foresight Trees for Object Retrieval from Clutter with Nonprehensile Rearrangementcited by 15
  6. 2021Extended Tree Search for Robot Task and Motion Planningcited by 14
  7. 2022Coarse-to-Fine Q-attention with Learned Path Rankingcited by 13
  8. 2022ReorientBot: Learning Object Reorientation for Specific-Posed Placementcited by 10
  9. 2022Bingham Policy Parameterization for 3D Rotations in Reinforcement Learningcited by 8
  10. 2022SafePicking: Learning Safe Object Extraction via Object-Level Mappingcited by 3
  11. 2021Hierarchical Policy for Non-prehensile Multi-object Rearrangement with Deep Reinforcement Learning and Monte Carlo Tree Searchcited by 1

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2; 2024: 5.

9 papers.

  1. 2022Masked World Models for Visual Controlcited by 170
  2. 2024Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulationcited by 93
  3. 2023Multi-View Masked World Models for Visual Robotic Manipulationcited by 80
  4. 2023Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasetscited by 58
  5. 2024PerAct2: Benchmarking and Learning for Robotic Bimanual Manipulation Taskscited by 37
  6. 2024BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmarkcited by 30
  7. 2022On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learningcited by 19
  8. 2024Continuous Control with Coarse-to-fine Reinforcement Learningcited by 17
  9. 2024Redundancy-aware Action Spaces for Robot Learningcited by 5