AI for Global Climate Cooperation Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N

Global cooperation on climate change mitigation is essential to limit temperature increases while supporting long-term, equitable economic growth and sustainable development. Achieving such cooperation among diverse regions, each with different incentives, in a dynamic environment shaped by complex political and economic factors, without a central authority, is a profoundly challenging game-theoretic problem. This article introduces RICE-N, a multi-region integrated assessment model that simulates the global climate, economy, and climate negotiations and agreements. RICE-N uses multi-agent reinforcement learning (MARL) to incentivize agents to develop strategic behaviors based on the environmental dynamics and the actions of others. We present two negotiation protocols: (1) Bilateral Negotiation, an example protocol and (2) Basic Club, inspired by Climate Clubs and the carbon border adjustment mechanism (Nordhaus, 2015; Commission, 2022). When we compare their impact against a no-negotiation baseline with various mitigation strategies, we find that both protocols significantly reduce temperature growth at the cost of a minor drop in production while ensuring a more equitable distribution of the emissions reduction costs.