analiza aiqbench
This study addresses the computational bottleneck of embedding high-fidelity climate simulators into reinforcement learning loops by training a recurrent surrogate model on 20,000 emission pathways. The resulting framework achieves near-simulator accuracy with a 1,000x speed-up in inference and over 100x faster end-to-end training for multi-agent systems. By validating policy fidelity through consistency tests like Kendall's tau, the work enables scalable experiments on complex multi-gas dynamics previously infeasible for standard RL approaches.
Climate Surrogates for Scalable Multi-Agent Reinforcement Learning: A Case Study with CICERO-SCM
arXiv:2510.07971v2 Announce Type: replace 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 the European Environment 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 $\approx\!4\!\times \!10^{-4}\,\mathrm{K}$) with $\sim\!1000\times$ faster one-step inference and yields $>\!100\times$ 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 $\tau$) 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.
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 the European Environment 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 $\approx\!4\!\times \!10^{-4}\,\mathrm{K}$) with $\sim\!1000\times$ faster one-step inference and yields $>\!100\times$ 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 $\tau$) 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.
Machine Learning (cs.LG); Multiagent Systems (cs.MA)
arXiv:2510.07971 [cs.LG]
(or arXiv:2510.07971v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2510.07971 Focus to learn more arXiv-issued DOI via DataCite
Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-ECAI 2026), pp. 7084-7092, 2026
https://doi.org/10.24963/ijcai.2026/788 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 253 cuvinte
Subiecte conexe
News
Quantum Computing Report · 25 iul. 2026
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · 17 sept. 2026
Mastering Agentic Techniques: AI Agent Reinforcement Learning
NVIDIA · 1 iul. 2026
The Alignment Problem: Computer Science Meets Analytic Philosophy
LessWrong · 18 oct. 2026