mlsanityData to 14 Oct 2026

GloCAL: Glocalized Curriculum-Aided Learning of Multiple Tasks with Application to Robotic Grasping

arXiv 2204.06835 ↗First posted 14 Apr 2022cs.RO cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The domain of robotics is challenging to apply deep reinforcement learning due to the need for large amounts of data and for ensuring safety during learning. Curriculum learning has shown good performance in terms of sample- efficient deep learning. In this paper, we propose an algorithm (named GloCAL) that creates a curriculum for an agent to learn multiple discrete tasks, based on clustering tasks according to their evaluation scores. From the highest-performing cluster, a global task representative of the cluster is identified for learning a global policy that transfers to subsequently formed new clusters, while the remaining tasks in the cluster are learned as local policies. The efficacy and efficiency of our GloCAL algorithm are compared with other approaches in the domain of grasp learning for 49 objects with varied object complexity and grasp difficulty from the EGAD! dataset. The results show that GloCAL is able to learn to grasp 100% of the objects, whereas other approaches achieve at most 86% despite being given 1.5 times longer training time.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 40 references that are in the map. First posted on arXiv 14 Apr 2022.

Builds on

26 of 40 references.

References · 26

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2015Continuous control with deep reinforcement learningcited by 3,407
  3. 2017Hindsight Experience Replaycited by 1,136
  4. 2018Learning Dexterous In-Hand Manipulationcited by 687
  5. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 373
  6. 2016Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collectioncited by 316
  7. 2019On The Power of Curriculum Learning in Training Deep Networkscited by 286
  8. 2018Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Researchcited by 260
  9. 2017Automatic Goal Generation for Reinforcement Learning Agentscited by 259
  10. 2017Automated Curriculum Learning for Neural Networkscited by 257
  11. 20196-DOF GraspNet: Variational Grasp Generation for Object Manipulationcited by 242
  12. 2015Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hourscited by 209
14 more
  1. 2020Automatic Curriculum Learning For Deep RL: A Short Surveycited by 150
  2. 2019Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environmentscited by 119
  3. 2020Automatic Curriculum Learning through Value Disagreementcited by 87
  4. 20196-DOF Grasping for Target-driven Object Manipulation in Cluttercited by 70
  5. 2020EGAD! an Evolved Grasping Analysis Dataset for diversity and reproducibility in robotic manipulationcited by 61
  6. 2020MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusioncited by 46
  7. 2018A survey on policy search algorithms for learning robot controllers in a handful of trialscited by 35
  8. 2020Verifiably Safe Exploration for End-to-End Reinforcement Learningcited by 34
  9. 2018Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methodscited by 33
  10. 2019Learning One-Shot Imitation from Humans without Humanscited by 33
  11. 2020Robotic Grasping using Deep Reinforcement Learningcited by 28
  12. 20196D Pose Estimation with Correlation Fusioncited by 6
  13. 2019Deep Reinforcement-Learning-based Driving Policy for Autonomous Road Vehiclescited by 5
  14. 2020Trying AGAIN instead of Trying Longer: Prior Learning for Automatic Curriculum Learningcited by 1

Built on by

Not cited yet.