# Coarse-to-Fine Q-attention with Learned Path Ranking

arXiv: https://arxiv.org/abs/2204.01571 · HTML: https://mlsanity.com/paper/2204.01571/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 4 Apr 2022.

## Builds on (most cited first, 16 of 16)

- [QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/1806.10293/) (2018)
- [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019)
- [Asymmetric Actor Critic for Image-Based Robot Learning](https://mlsanity.com/paper/1710.06542/) (2017)
- [Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks](https://mlsanity.com/paper/1812.07252/) (2018)
- [Value Iteration Networks](https://mlsanity.com/paper/1602.02867/) (2016)
- [Sim-to-Real Reinforcement Learning for Deformable Object Manipulation](https://mlsanity.com/paper/1806.07851/) (2018)
- [Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation](https://mlsanity.com/paper/2106.12534/) (2021)
- [Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation](https://mlsanity.com/paper/2105.14829/) (2021)
- [Motion Planning Networks](https://mlsanity.com/paper/1806.05767/) (2018)
- [Composable Deep Reinforcement Learning for Robotic Manipulation](https://mlsanity.com/paper/1803.06773/) (2018)
- [PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-based Planning](https://mlsanity.com/paper/1710.03937/) (2017)
- [Object Rearrangement Using Learned Implicit Collision Functions](https://mlsanity.com/paper/2011.10726/) (2020)
- [Differentiable Gaussian Process Motion Planning](https://mlsanity.com/paper/1907.09591/) (2019)
- [Neural Path Planning: Fixed Time, Near-Optimal Path Generation via Oracle Imitation](https://mlsanity.com/paper/1904.11102/) (2019)
- [3D Simulation for Robot Arm Control with Deep Q-Learning](https://mlsanity.com/paper/1609.03759/) (2016)
- [Bingham Policy Parameterization for 3D Rotations in Reinforcement Learning](https://mlsanity.com/paper/2202.03957/) (2022)

## Built on by (most cited first, 13 of 13)

- [Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation](https://mlsanity.com/paper/2209.05451/) (2022)
- [Masked World Models for Visual Control](https://mlsanity.com/paper/2206.14244/) (2022)
- [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)
- [Multi-View Masked World Models for Visual Robotic Manipulation](https://mlsanity.com/paper/2302.02408/) (2023)
- [Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation](https://mlsanity.com/paper/2411.18623/) (2024)
- [BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark](https://mlsanity.com/paper/2407.07788/) (2024)
- [On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning](https://mlsanity.com/paper/2206.03271/) (2022)
- [Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulation](https://mlsanity.com/paper/2506.09990/) (2025)
- [Coarse-to-fine Q-attention with Tree Expansion](https://mlsanity.com/paper/2204.12471/) (2022)
- [KEMO: Event-Driven Keyframe Memory for Long-Horizon Robot Manipulation with VLA Policies](https://mlsanity.com/paper/2606.23589/) (2026)
- [Lift3D-VLA: Lifting VLA Models to 3D Geometry and Dynamics-Aware Manipulation](https://mlsanity.com/paper/2607.06564/) (2026)
- [SkiP: When to Skip and When to Refine for Efficient Robot Manipulation](https://mlsanity.com/paper/2605.15536/) (2026)

## Abstract (arXiv)

We propose Learned Path Ranking (LPR), a method that accepts an end-effector goal pose, and learns to rank a set of goal-reaching paths generated from an array of path generating methods, including: path planning, Bezier curve sampling, and a learned policy. The core idea being that each of the path generation modules will be useful in different tasks, or at different stages in a task. When LPR is added as an extension to C2F-ARM, our new system, C2F-ARM+LPR, retains the sample efficiency of its predecessor, while also being able to accomplish a larger set of tasks; in particular, tasks that require very specific motions (e.g. opening toilet seat) that need to be inferred from both demonstrations and exploration data. In addition to benchmarking our approach across 16 RLBench tasks, we also learn real-world tasks, tabula rasa, in 10-15 minutes, with only 3 demonstrations.