Towards Sustainable Investment Policies Informed by Opponent Shaping

ICLR 2026 Conference Submission19358 Authors

Keywords: Climate Change, Social Dilemmas, Multi Agent Reinforcement Learning, Opponent Shaping, Policy Making

TL;DR: We determine the conditions in which InvestESG, a MARL simulator of investments under climate risk, is a social dilemma. Then we apply opponent shaping to it and provide insights on how the resulting policies can inform policy making.

Abstract: Addressing climate change requires global coordination, yet rational economic actors often prioritize immediate gains over collective welfare, resulting in social dilemmas. InvestESG is a recently proposed multi-agent simulation that captures the dynamic interplay between investors and companies under climate risk. We provide a formal characterization of the conditions under which InvestESG exhibits an intertemporal social dilemma, deriving theoretical thresholds at which individual incentives diverge from collective welfare. Building on this, we apply Advantage Alignment, a scalable opponent shaping algorithm shown to be effective in general-sum games, to influence agent learning in InvestESG. We offer theoretical insights into why Advantage Alignment systematically favors socially beneficial equilibria by biasing learning dynamics toward cooperative outcomes. Our results demonstrate that strategically shaping the learning processes of economic agents can result in better outcomes that could inform policy mechanisms to better align market incentives with long-term sustainability goals.

Primary Area: other topics in machine learning (i.e., none of the above)

Submission Number: 19358