English

On Reducing Undesirable Behavior in Deep Reinforcement Learning Models

Machine Learning 2023-09-12 v2

Abstract

Deep reinforcement learning (DRL) has proven extremely useful in a large variety of application domains. However, even successful DRL-based software can exhibit highly undesirable behavior. This is due to DRL training being based on maximizing a reward function, which typically captures general trends but cannot precisely capture, or rule out, certain behaviors of the system. In this paper, we propose a novel framework aimed at drastically reducing the undesirable behavior of DRL-based software, while maintaining its excellent performance. In addition, our framework can assist in providing engineers with a comprehensible characterization of such undesirable behavior. Under the hood, our approach is based on extracting decision tree classifiers from erroneous state-action pairs, and then integrating these trees into the DRL training loop, penalizing the system whenever it performs an error. We provide a proof-of-concept implementation of our approach, and use it to evaluate the technique on three significant case studies. We find that our approach can extend existing frameworks in a straightforward manner, and incurs only a slight overhead in training time. Further, it incurs only a very slight hit to performance, or even in some cases - improves it, while significantly reducing the frequency of undesirable behavior.

Keywords

Cite

@article{arxiv.2309.02869,
  title  = {On Reducing Undesirable Behavior in Deep Reinforcement Learning Models},
  author = {Ophir M. Carmel and Guy Katz},
  journal= {arXiv preprint arXiv:2309.02869},
  year   = {2023}
}
R2 v1 2026-06-28T12:14:05.055Z