---
title: "DEPLOY-RL: Active Boundary Discovery and Conservative Certification for Deployable Reinforcement Learning in Safety-Critical Continuous Processes"
authors:
  - "Yeojin Jang"
  - "Minu Baek"
  - "Gihun Gil"
  - "Minsung Jung"
  - "Beomdo Park"
  - "Woohyeon Kwon"
  - "Hyeonseok Jang"
  - "Junseong Park"
  - "Neha Sengar"
  - "Andres Saurez"
  - "Sangkeum Lee"
doi: "10.24963/ijcai.2026/718"
url: "https://ijcai.org/proceedings/2026/718"
pdf: "https://ijcai.org/proceedings/2026/0718.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "6454-6461"
track: "AI4Tech: AI Enabling Technologies"
keywords:
  - "Advanced AI4Tech: Data-driven AI4Tech"
  - "Advanced AI4Tech: AI4Tech foundations"
  - "Domain-specific AI4Tech: AI4Safety"
  - "Domain-specific AI4Tech: AI4Manufacturing"
---

# DEPLOY-RL: Active Boundary Discovery and Conservative Certification for Deployable Reinforcement Learning in Safety-Critical Continuous Processes

Yeojin Jang, Minu Baek, Gihun Gil, Minsung Jung, Beomdo Park, Woohyeon Kwon, Hyeonseok Jang, Junseong Park, Neha Sengar, Andres Saurez, Sangkeum Lee

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 6454-6461. DOI: [10.24963/ijcai.2026/718](https://doi.org/10.24963/ijcai.2026/718)

## Abstract

Reinforcement learning (RL) policies often outperform classical controllers in simulation, yet rarely reach production in safety-critical processes. The barrier is that there is no principled way to answer “Is this policy safe to deploy?” with statistical guarantees. We introduce DEPLOY-RL, a post-training certification framework built on one key insight: deployment certification requires discovering where failures occur (boundary discovery), not measuring how much everywhere (uniform reconstruction). Our contributions: (1) a contract-coupled acquisition function that concentrates sampling on certification-critical boundaries, achieving ≈ 2× sample efficiency with a semi-empirical ambiguity reduction bound (domain-calibrated convergence guarantee); (2) conformal risk control providing finite-sample false-go guarantees (≤ α) under explicit deployment contracts; (3) a three-way decision framework (Deploy/No-Deploy/Abstain) with fail-safe PID/MPC fallback. In simulations on papermaking (industrial digital twin) and Tennessee Eastman (public benchmark), DEPLOY-RL achieves 4.4% false-go rate (vs. 8.6% for the best baseline) while retaining 88.6% policy coverage—the only method achieving <5% false-go with >85% coverage among 14 baselines under our evaluation protocol.