A Demonstration Of Stability-Plasticity Imbalance In Multi-Agent, Decomposition-Based Learning
Keywords
Decomposition-based reinforcement learning; Layered learning; Stability-plasticity dilemma
Abstract
Layered learning is a machine learning paradigm used in conjunction with direct-policy search reinforcement learning methods to find high performance agent behaviors for complex tasks. At its core, layered learning is a decomposition-based paradigm that shares many characteristics with robot shaping, transfer learning, hierarchical decomposition, and incremental learning. Previous studies have provided evidence that layered learning has the ability to outperform standard monolithic methods of learning in many cases. The dilemma of balancing stability and plasticity is a common problem in machine learning that causes learning agents to compromise between retaining learned information to perform a task with new incoming information. Although existing work implies that there is a stability-plasticity imbalance that greatly limits layered learning agents' ability to learn optimally, no work explicitly verifies the existence of the imbalance or its causes. This work investigates the stability-plasticity imbalance and demonstrates that indeed, layered learning heavily favors plasticity, which can cause learned subtask proficiency to be lost when new tasks are learned. We conclude by identifying potential causes of the imbalance in layered learning and provide high level advice about how to mitigate the imbalance's negative effects.
Publication Date
3-2-2016
Publication Title
Proceedings - 2015 IEEE 14th International Conference on Machine Learning and Applications, ICMLA 2015
Number of Pages
1070-1075
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/ICMLA.2015.106
Copyright Status
Unknown
Socpus ID
84969590506 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84969590506
STARS Citation
Mondesire, Sean C. and Wiegand, R. Paul, "A Demonstration Of Stability-Plasticity Imbalance In Multi-Agent, Decomposition-Based Learning" (2016). Scopus Export 2015-2019. 4191.
https://stars.library.ucf.edu/scopus2015/4191