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

arXiv: https://arxiv.org/abs/2204.06835 · HTML: https://mlsanity.com/paper/2204.06835/

## 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 (most cited first, 26 of 26)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection](https://mlsanity.com/paper/1603.02199/) (2016)
- [On The Power of Curriculum Learning in Training Deep Networks](https://mlsanity.com/paper/1904.03626/) (2019)
- [Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research](https://mlsanity.com/paper/1802.09464/) (2018)
- [Automatic Goal Generation for Reinforcement Learning Agents](https://mlsanity.com/paper/1705.06366/) (2017)
- [Automated Curriculum Learning for Neural Networks](https://mlsanity.com/paper/1704.03003/) (2017)
- [6-DOF GraspNet: Variational Grasp Generation for Object Manipulation](https://mlsanity.com/paper/1905.10520/) (2019)
- [Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours](https://mlsanity.com/paper/1509.06825/) (2015)
- [Automatic Curriculum Learning For Deep RL: A Short Survey](https://mlsanity.com/paper/2003.04664/) (2020)
- [Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments](https://mlsanity.com/paper/1910.07224/) (2019)
- [Automatic Curriculum Learning through Value Disagreement](https://mlsanity.com/paper/2006.09641/) (2020)
- [6-DOF Grasping for Target-driven Object Manipulation in Clutter](https://mlsanity.com/paper/1912.03628/) (2019)
- [EGAD! an Evolved Grasping Analysis Dataset for diversity and reproducibility in robotic manipulation](https://mlsanity.com/paper/2003.01314/) (2020)
- [MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusion](https://mlsanity.com/paper/2004.04336/) (2020)
- [A survey on policy search algorithms for learning robot controllers in a handful of trials](https://mlsanity.com/paper/1807.02303/) (2018)
- [Verifiably Safe Exploration for End-to-End Reinforcement Learning](https://mlsanity.com/paper/2007.01223/) (2020)
- [Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods](https://mlsanity.com/paper/1802.10264/) (2018)
- [Learning One-Shot Imitation from Humans without Humans](https://mlsanity.com/paper/1911.01103/) (2019)
- [Robotic Grasping using Deep Reinforcement Learning](https://mlsanity.com/paper/2007.04499/) (2020)
- [6D Pose Estimation with Correlation Fusion](https://mlsanity.com/paper/1909.12936/) (2019)
- [Deep Reinforcement-Learning-based Driving Policy for Autonomous Road Vehicles](https://mlsanity.com/paper/1907.05246/) (2019)
- [Trying AGAIN instead of Trying Longer: Prior Learning for Automatic Curriculum Learning](https://mlsanity.com/paper/2004.03168/) (2020)

## 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.