---
title: "Climate Surrogates for Scalable Multi-Agent Reinforcement Learning: A Case Study with CICERO-SCM"
authors:
  - "Oskar Bohn Lassen"
  - "Serio Agriesti"
  - "Filipe Rodrigues"
  - "Blaz Kurnik"
  - "Francisco Pereira"
doi: "10.24963/ijcai.2026/788"
url: "https://ijcai.org/proceedings/2026/788"
pdf: "https://ijcai.org/proceedings/2026/0788.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "7084-7092"
track: "AI and Social Good"
keywords:
  - "Machine Learning: Machine Learning"
  - "AI Ethics, Trust, Fairness: AI Ethics, Trust, Fairness"
  - "Agent-based and Multi-agent Systems: Agent-based and Multi-agent Systems"
  - "Humans and AI: Humans and AI"
---

# Climate Surrogates for Scalable Multi-Agent Reinforcement Learning: A Case Study with CICERO-SCM

Oskar Bohn Lassen, Serio Agriesti, Filipe Rodrigues, Blaz Kurnik, Francisco Pereira

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 7084-7092. DOI: [10.24963/ijcai.2026/788](https://doi.org/10.24963/ijcai.2026/788)

## Abstract

Climate policy analysis requires models that capture multi-gas climate effects, but such models are too slow to embed in reinforcement learning loops at scale. In collaboration with a pan-European public-sector environmental agency, we develop a multi-agent reinforcement learning (MARL) framework that integrates a higher-fidelity climate surrogate as the environment transition, enabling regional agents to learn policies under multi-gas dynamics. We train a recurrent surrogate on 20,000 multi-gas emission pathways to emulate CICERO-SCM. The surrogate achieves near-simulator accuracy (global-mean temperature RMSE ≈ 4 × 10⁻⁴ K) with ∼1000× faster one-step inference and yields >100× end-to-end MARL training speed-up. We show policy agreement with the simulator in tractable settings and propose a replay- and rank-consistency test (Kendall’s τ) for assessing policy fidelity when simulator-in-the-loop training is infeasible. This enables large-scale multi-agent policy experiments while retaining high-fidelity multi-gas climate response.