Improving International Climate Policy via Mutually Conditional Binding Commitments

TL;DR

This paper enhances the RICE-N simulation and multi-agent reinforcement learning framework to better model international climate negotiations by incorporating social factors, stakeholder agents, and improved algorithms, aiming for more realistic policy decision-making.

Contribution

It introduces significant improvements to the RICE-N framework, including social factors, stakeholder agents, and advanced algorithms, to bridge the gap between simulation and real-world climate negotiations.

Findings

Proposed inclusion of social and stakeholder agents in simulations.

Enhanced reinforcement learning algorithms for better negotiation modeling.

Identified the need for further testing to validate improvements.

Abstract

This paper proposes enhancements to the RICE-N simulation and multi-agent reinforcement learning framework to improve the realism of international climate policy negotiations. Acknowledging the framework's value, we highlight the necessity of significant enhancements to address the diverse array of factors in modeling climate negotiations. Building upon our previous work on the "Conditional Commitments Mechanism" (CCF mechanism) we discuss ways to bridge the gap between simulation and reality. We suggest the inclusion of a recommender or planner agent to enhance coordination, address the Real2Sim gap by incorporating social factors and non-party stakeholder sub-agents, and propose enhancements to the underlying Reinforcement Learning solution algorithm. These proposed improvements aim to advance the evaluation and formulation of negotiation protocols for more effective international climate policy decision-making in Rice-N. However, further experimentation and testing are required to determine the implications and effectiveness of these suggestions.