mlsanityData to 14 Oct 2026

Margin Play: A Multi-Agent System For Public Policy Analysis In The Brazilian Equatorial Margin

arXiv 2606.02614 ↗First posted 26 May 2026cs.CE cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The Brazilian Equatorial Margin (BEM) is Brazil's next offshore oil frontier, with operations expected to begin in 2026 in the Foz do Amazonas basin. Its assets are fiscally and territorially linked primarily to Maranhao -- the state with the lowest HDI in the Federation (0.676, IBGE 2022). This raises the central policy question: under what conditions does BEM exploration generate net positive externalities for Maranhao? The problem is intrinsically multi-agent: the Federal Government seeks revenue and energy security; the state seeks regional welfare under constitutional royalty earmarking; the operator maximizes profit under risk; ANP and IBAMA hold conflicting mandates; and Amazonian communities prioritize territorial and environmental vectors over monetary income. We present Margin Play, a Multi-Agent Reinforcement Learning (MARL) system simulating these tensions under Brazilian empirical calibration and classical economic literature. It implements six agents under the CTDE paradigm, trained with BRO-MARL. Results from 60,000 episodes across six scenarios indicate the answer is conditional on the institutional regime: under the reference baseline, the welfare gain is marginal (Waval approx. 1.68), whereas the MA-Prospero configuration yields Delta W = +17.5% and Delta Rcom = +21.3%, with a lower environmental liability (Eamb = 0.048 vs. 0.076). The fundamental problem is not a trade-off between production and welfare, but the choice of public policy regime linked to exploration.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 7 of its 49 references that are in the map. First posted on arXiv 26 May 2026.

Builds on

7 of 49 references.

References · 7

  1. 2015Continuous control with deep reinforcement learningcited by 3,407
  2. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  3. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  4. 2017A Distributional Perspective on Reinforcement Learningcited by 765
  5. 2020Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Criticscited by 165
  6. 2022Revealing Robust Oil and Gas Company Macro-Strategies using Deep Multi-Agent Reinforcement Learningcited by 4
  7. 2021PolicySpace2: modeling markets and endogenous public policiescited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Optimizing Information Asset Investment Strategies in the Exploratory Phase of the Oil and Gas Industry: A Reinforcement Learning Approach
  2. 2024InvestESG: A multi-agent reinforcement learning benchmark for studying climate investment as a social dilemma
  3. 2023A Multi-agent Reinforcement Learning Study of Emergence of Social Classes out of Arbitrary Governance: The Role of Environment
  4. 2025Multi-Agent Reinforcement Learning Simulation for Environmental Policy Synthesis
  5. 2025Exploring Equity of Climate Policies using Multi-Agent Multi-Objective Reinforcement Learning
  6. 2024Empirical Equilibria in Agent-based Economic systems with Learning agents
  7. 2025Natural-gas storage modelling by deep reinforcement learning
  8. 2026Learning Principal-Agent Contracts for Equitable Smallholder Carbon Farming under Moral Hazard and Adverse Selection