Paper Detail

Explainable Reinforcement Learning via Physics-Aware Policy Distillation

Shaker Al-Tamari, Waled Kadour

Browse

Workflow Queues

arxiv Score 11.3

Published 2026-07-27 · First seen 2026-07-28

General AI

Open paper source

Abstract

In safety-critical sectors such as robotics and automotive engineering, the deployment of Deep Reinforcement Learning (DRL) is often hindered by the black-box nature of deep neural networks. This lack of transparency poses significant challenges for regulatory compliance and human-agent trust. This paper presents an experimental study aimed at making high-performance continuous control DRL systems interpretable. A policy distillation framework is implemented using the classic Inverted Pendulum benchmark. A high-performance Twin Delayed DDPG (TD3) agent serves as an opaque, continuous teacher model, whose policy is distilled into an interpretable student surrogate based on a shallow Decision Tree. By leveraging a custom physics-aware feature and "Noisy Oracle Rollouts" for dataset generation, the distillation process achieves performance equivalent to the expert teacher. Furthermore, comparative control theory analysis reveals a fundamental trade-off: transitioning from continuous to discrete rule-based control induces high-frequency Bang-Bang actuation and a stable bimodal limit cycle. Simulation results indicate that Bounded-Input Bounded-Output (BIBO) stability is maintained while providing both global and local interpretability for safe autonomous systems.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

Similar Papers

Solving Physics Olympiad via Reinforcement Learning on Physics Simulators 2026-04-13 · Score 17.3 General AI PRISM: Pre-alignment via Black-box On-policy Distillation for Multimodal Reinforcement Learning 2026-04-30 · Score 16.3 General AI SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning 2026-07-16 · Score 15.0 General AI Reinforcement Learning via Value Gradient Flow 2026-04-15 · Score 10.5 General AI Progressive Agent Skill Generation via Reinforcement Learning 2026-08-03 · Score 10.5 Research Track A · General AI

BibTeX

@article{altamari2026explainable,
  title = {Explainable Reinforcement Learning via Physics-Aware Policy Distillation},
  author = {Shaker Al-Tamari and Waled Kadour},
  year = {2026},
  abstract = {In safety-critical sectors such as robotics and automotive engineering, the deployment of Deep Reinforcement Learning (DRL) is often hindered by the black-box nature of deep neural networks. This lack of transparency poses significant challenges for regulatory compliance and human-agent trust. This paper presents an experimental study aimed at making high-performance continuous control DRL systems interpretable. A policy distillation framework is implemented using the classic Inverted Pendulum b},
  url = {https://arxiv.org/abs/2607.24672},
  keywords = {cs.LG},
  eprint = {2607.24672},
  archiveprefix = {arXiv},
}

Metadata

{}