Accelerating Reinforcement Learning for Reaching Using Continuous Curriculum Learning
- 1 July 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Abstract
Reinforcement learning has shown great promise in the training of robot behavior due to the sequential decision making characteristics. However, the required enormous amount of interactive and informative training data provides the major stumbling block for progress. In this study, we focus on accelerating reinforcement learning (RL) training and improving the performance of multi-goal reaching tasks. Specifically, we propose a precision-based continuous curriculum learning (PCCL) method in which the requirements are gradually adjusted during the training process, instead of fixing the parameter in a static schedule. To this end, we explore various continuous curriculum strategies for controlling a training process. This approach is tested using a Universal Robot 5e in both simulation and real-world multi-goal reach experiments. Experimental results support the hypothesis that a static training schedule is suboptimal, and using an appropriate decay function for curriculum learning provides superior results in a faster way.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- OptLayer - Practical Constrained Optimization for Deep Reinforcement Learning in the Real World2018
- Towards lifelong assistive robotics: A tight coupling between object perception and manipulationNeurocomputing, 2018
- Virtual-to-real deep reinforcement learning: Continuous control of mobile robots for mapless navigation2017
- Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates2017
- Deep learning for detecting robotic graspsThe International Journal of Robotics Research, 2015
- Human-level control through deep reinforcement learningNature, 2015
- Curriculum learning2009
- Reinforcement Learning in Continuous Action Spaces2007
- Automatic writer identification using connected-component contours and edge-based features of uppercase Western scriptIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Reinforcement today.American Psychologist, 1958