mlsanityData to 14 Oct 2026

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

arXiv 2411.06733 ↗First posted 11 Nov 2024cs.LG cs.ROcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

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.

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.

Builds on

22 of 24 references.

References · 22

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  5. 2016Generative Adversarial Imitation Learningcited by 1,597
  6. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 715
  7. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 689
  8. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 483
  9. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 457
  10. 2023ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skillscited by 327
  11. 2017Distral: Robust Multitask Reinforcement Learningcited by 233
  12. 2021Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulationcited by 209
10 more
  1. 2022SoftGroup for 3D Instance Segmentation on Point Cloudscited by 200
  2. 2021ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrationscited by 197
  3. 2021FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimationcited by 144
  4. 2021Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observabilitycited by 109
  5. 2022FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objectscited by 91
  6. 2017Divide-and-Conquer Reinforcement Learningcited by 48
  7. 2022Learning to Detect Mobile Objects from LiDAR Scans Without Labelscited by 44
  8. 2022Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point Cloudscited by 32
  9. 2022Improving Policy Optimization with Generalist-Specialist Learningcited by 20
  10. 2023On the Efficacy of 3D Point Cloud Reinforcement Learningcited by 11

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Improving Generalization on the ProcGen Benchmark with Simple Architectural Changes and Scale
  2. 2025Robust Finetuning of Vision-Language-Action Robot Policies via Parameter Merging
  3. 2025Generalizable Hierarchical Skill Learning via Object-Centric Representation
  4. 2024RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning
  5. 2025Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation
  6. 2024Learning Generalizable 3D Manipulation With 10 Demonstrations
  7. 2025On Generalization Across Environments In Multi-Objective Reinforcement Learning
  8. 2026Robust Successor Features