English

Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation

Machine Learning 2022-09-02 v2 Artificial Intelligence

Abstract

The powerful learning ability of deep neural networks enables reinforcement learning agents to learn competent control policies directly from continuous environments. In theory, to achieve stable performance, neural networks assume i.i.d. inputs, which unfortunately does no hold in the general reinforcement learning paradigm where the training data is temporally correlated and non-stationary. This issue may lead to the phenomenon of "catastrophic interference" and the collapse in performance. In this paper, we present IQ, i.e., interference-aware deep Q-learning, to mitigate catastrophic interference in single-task deep reinforcement learning. Specifically, we resort to online clustering to achieve on-the-fly context division, together with a multi-head network and a knowledge distillation regularization term for preserving the policy of learned contexts. Built upon deep Q networks, IQ consistently boosts the stability and performance when compared to existing methods, verified with extensive experiments on classic control and Atari tasks. The code is publicly available at: https://github.com/Sweety-dm/Interference-aware-Deep-Q-learning.

Keywords

Cite

@article{arxiv.2109.00525,
  title  = {Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation},
  author = {Tiantian Zhang and Xueqian Wang and Bin Liang and Bo Yuan},
  journal= {arXiv preprint arXiv:2109.00525},
  year   = {2022}
}

Comments

21 pages

R2 v1 2026-06-24T05:36:16.918Z