# GSL-PCD: Improving Generalist-Specialist Learning with Point Cloud Feature-based Task Partitioning

arXiv: https://arxiv.org/abs/2411.06733 · HTML: https://mlsanity.com/paper/2411.06733/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 22 of its 24 references that are in the map.
- First posted on arXiv 11 Nov 2024.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 22 of 22)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [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)
- [Leveraging Procedural Generation to Benchmark Reinforcement Learning](https://mlsanity.com/paper/1912.01588/) (2019)
- [Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1812.07179/) (2018)
- [ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills](https://mlsanity.com/paper/2302.04659/) (2023)
- [Distral: Robust Multitask Reinforcement Learning](https://mlsanity.com/paper/1707.04175/) (2017)
- [Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation](https://mlsanity.com/paper/2112.05124/) (2021)
- [SoftGroup for 3D Instance Segmentation on Point Clouds](https://mlsanity.com/paper/2203.01509/) (2022)
- [ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations](https://mlsanity.com/paper/2107.14483/) (2021)
- [FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation](https://mlsanity.com/paper/2103.02242/) (2021)
- [Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability](https://mlsanity.com/paper/2107.06277/) (2021)
- [FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objects](https://mlsanity.com/paper/2205.04382/) (2022)
- [Divide-and-Conquer Reinforcement Learning](https://mlsanity.com/paper/1711.09874/) (2017)
- [Learning to Detect Mobile Objects from LiDAR Scans Without Labels](https://mlsanity.com/paper/2203.15882/) (2022)
- [Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point Clouds](https://mlsanity.com/paper/2210.07442/) (2022)
- [Improving Policy Optimization with Generalist-Specialist Learning](https://mlsanity.com/paper/2206.12984/) (2022)
- [On the Efficacy of 3D Point Cloud Reinforcement Learning](https://mlsanity.com/paper/2306.06799/) (2023)

## Abstract (arXiv)

Generalization in Deep Reinforcement Learning (DRL) across unseen environment variations often requires training over a diverse set of scenarios. Many existing DRL algorithms struggle with efficiency when handling numerous variations. The Generalist-Specialist Learning (GSL) framework addresses this by first training a generalist model on all variations, then creating specialists from the generalist's weights, each focusing on a subset of variations. The generalist then refines its learning with assistance from the specialists. However, random task partitioning in GSL can impede performance by assigning vastly different variations to the same specialist, often resulting in each specialist focusing on only one variation, which raises computational costs. To improve this, we propose Generalist-Specialist Learning with Point Cloud Feature-based Task Partitioning (GSL-PCD). Our approach clusters environment variations based on features extracted from object point clouds and uses balanced clustering with a greedy algorithm to assign similar variations to the same specialist. Evaluations on robotic manipulation tasks from the ManiSkill benchmark demonstrate that point cloud feature-based partitioning outperforms vanilla partitioning by 9.4%, with a fixed number of specialists, and reduces computational and sample requirements by 50% to achieve comparable performance.