LGSep 6, 2023

On Reducing Undesirable Behavior in Deep Reinforcement Learning Models

arXiv:2309.02869v2h-index: 1
Originality Incremental advance
AI Analysis

This addresses safety and reliability issues in DRL-based software for engineers and developers, though it is incremental as it extends existing frameworks.

The paper tackles the problem of undesirable behavior in deep reinforcement learning models by proposing a framework that integrates decision tree classifiers into the training loop to penalize errors, resulting in a significant reduction in undesirable behavior with only slight performance overhead or even improvement in some cases.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes