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 geopolitical 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 encourage agents to develop strategic behaviors based on the environmental dynamics and the actions of the others. We present two negotiation protocols: (1) Bilateral Negotiation, an exemplary protocol and (2) Basic Club, inspired from Climate Clubs and the carbon border adjustment mechanism (Nordhaus, 2015; Comissions, 2022). We compare their impact against a no-negotiation baseline with various mitigation strategies, showing that both protocols significantly reduce temperature growth at the cost of a minor drop in production while ensuring a more equitable distribution of the emission reduction costs.

Artificial Intelligence (AI) holds promise as a technology that can be used to improve government and economic policy-making. This paper proposes a new research agenda towards this end by introducingSocial Environment Design, a general framework for the use of AI in automated policy-making that connects with the Reinforcement Learning, EconCS, and Computational Social Choice communities. The framework seeks to capture general economic environments, includes voting on policy objectives, and gives a direction for the systematic analysis of government and economic policy through AI simulation. We highlight key open problems for future research in AI-based policymaking. By solving these challenges, we hope to achieve various social welfare objectives, thereby promoting more ethical and responsible decision making.

Artificial Intelligence (AI) holds promise as a technology that can be used to improve government and economic policy-making. This paper proposes a new research agenda towards this end by introducing Social Environment Design, a general framework for the use of AI for automated policy-making that connects with the Reinforcement Learning, EconCS, and Computational Social Choice communities. The framework seeks to capture general economic environments, includes voting on policy objectives, and gives a direction for the systematic analysis of government and economic policy through AI simulation. We highlight key open problems for future research in AI-based policy-making. By solving these challenges, we hope to achieve various social welfare objectives, thereby promoting more ethical and responsible decision making.

We study how a principal can efficiently and effectively intervene on the rewards of a previously unseen learning agent in order to induce desirable outcomes. This is relevant to many real-world settings like auctions or taxation, where the principal may not know the learning behavior nor the rewards of real people. Moreover, the principal should be few-shot adaptable and minimize the number of interventions, because interventions are often costly. We introduce MERMAIDE, a model-based meta-learning framework to train a principal that can quickly adapt to out-of-distribution agents with different learning strategies and reward functions. We validate this approach step-by-step. First, in a Stackelberg setting with a best-response agent, we show that meta-learning enables quick convergence to the theoretically known Stackelberg equilibrium at test time, although noisy observations severely increase the sample complexity. We then show that our model-based meta-learning approach is cost-effective in intervening on bandit agents with unseen explore-exploit strategies. Finally, we outperform baselines that use either meta-learning or agent behavior modeling, in both $0$-shot and $K=1$-shot settings with partial agent information.

Mechanism design (MD) studies how rules and rewards shape the behavior of intelligent agents, e.g., in auctions or the economy. Simulations with AI agents are powerful tools for MD, but real-world agents may behave and learn differently than simulated agents under a given mechanism. Also, the mechanism designer may not fully observe an agent's learning strategy or rewards, and executing a mechanism may be costly, e.g., enforcing a tax might require extra labor. Hence, it is key to design robust adaptive mechanisms that generalize well to agents with unseen (learning) behavior, are few-shot adaptable, and are cost-efficient. Here, we introduce MERMADE, a model-based meta-learning framework to learn mechanisms that can quickly adapt when facing out-of-distribution agents with different learning strategies and reward functions. First, we show that meta-learning allows adapting to the theoretically known and appropriate Stackelberg equilibrium in a simple matrix game at meta-test time, with few interactions with the agent. Second, with bandit agents, we show empirically that our approach yields strong meta-test time performance against agents with various unseen explore-exploit behaviors. Finally, we outperform baselines that separately use either meta-learning or agent behavior modeling to learn a cost-effective mechanism that is $K$-shot adaptable with only partial information about the agents.

The international community must collaborate to mitigate climate change and sustain economic growth. However, collaboration is hard to achieve, partly because no global authority can ensure compliance with international climate agreements. Combining AI with climate-economic simulations offers a promising solution to design international frameworks, including negotiation protocols and climate agreements, that promote and incentivize collaboration. In addition, these frameworks should also have policy goals fulfillment, and sustained commitment, taking into account climate-economic dynamics and strategic behaviors. These challenges require an interdisciplinary approach across machine learning, economics, climate science, law, policy, ethics, and other fields. Towards this objective, we organized AI for Global Climate Cooperation, a Mila competition in which teams submitted proposals and analyses of international frameworks, based on (modifications of) RICE-N, an AI-driven integrated assessment model (IAM). In particular, RICE-N supports modeling regional decision-making using AI agents. Furthermore, the IAM then models the climate-economic impact of those decisions into the future. Whereas the first track focused only on performance metrics, the proposals submitted to the second track were evaluated both quantitatively and qualitatively. The quantitative evaluation focused on a combination of (i) the degree of mitigation of global temperature rise and (ii) the increase in economic productivity. On the other hand, an interdisciplinary panel of human experts in law, policy, sociology, economics and environmental science, evaluated the solutions qualitatively. In particular, the panel considered the effectiveness, simplicity, feasibility, ethics, and notions of climate justice of the protocols. In the third track, the participants were asked to critique and improve RICE-N.

We study the behavior of an economic platform (e.g., Amazon, Uber Eats, Instacart) under shocks, such as COVID-19 lockdowns, and the effect of different regulation considerations. To this end, we develop a multi-agent simulation environment of a platform economy in a multi-period setting where shocks may occur and disrupt the economy. Buyers and sellers are heterogeneous and modeled as economically-motivated agents, choosing whether or not to pay fees to access the platform. We use deep reinforcement learning to model the fee-setting and matching behavior of the platform, and consider two major types of regulation frameworks: (1) taxation policies and (2) platform fee restrictions. We offer a number of simulated experiments that cover different market settings and shed light on regulatory tradeoffs. Our results show that while many interventions are ineffective with a sophisticated platform actor, we identify a particular kind of regulation—fixing fees to the optimal, no-shock fees while still allowing a platform to choose how to match buyers and sellers—as holding promise for promoting the efficiency and resilience of the economic system.

We study the problem of training a principal in a multi-agent general-sum game using reinforcement learning (RL). Learning a robust principal policy requires anticipating the worst possible strategic responses of other agents, which is generally NP-hard. However, we show that no-regret dynamics can identify these worst-case responses in poly-time in smooth games. We propose a framework that uses this policy evaluation method for efficiently learning a robust principal policy using RL. This framework can be extended to provide robustness to boundedly rational agents too. Our motivating application is automated mechanism design: we empirically demonstrate our framework learns robust mechanisms in both matrix games and complex spatiotemporal games. In particular, we learn a dynamic tax policy that improves the welfare of a simulated trade-and-barter economy by 15%, even when facing previously unseen boundedly rational RL taxpayers.

Real-world economies can be modeled as a network with many heterogeneous and strategic agents. In this setting, it is very challenging to find optimal mechanisms, e.g., taxes, 1) when taking strategic best responses into account and 2) even when using restrictive assumptions, e.g., that supply always meets demand. Deep multi-agent reinforcement learning (MARL) is a natural framework to learn mechanisms and model strategic best responses, but independent MARL often collapses to trivial solutions (e.g., where nobody works) as joint exploration severely distorts rewards and constraints. Here, we show how to use structured learning curricula and GPU-accelerated simulations to find non-trivial solutions in networks with many heterogeneous agents. We validate our approach in models with 100 worker-consumers, 10 firms, and a social planner who taxes and redistributes. We use empirical best-response analyses across agent types to show that it is difficult for agents to benefit by deviating from the learned solutions. In particular, we find income and corporate taxes that achieve 15% higher social welfare compared to baselines.

Comprehensive global cooperation is essential to limit global temperature increases while continuing economic development, e.g., reducing severe inequality or achieving long-term economic growth. Achieving long-term cooperation on climate change mitigation with n strategic agents poses a complex game-theoretic problem. For example, agents may negotiate and reach climate agreements, but there is no central authority to enforce adherence to those agreements. Hence, it is critical to design negotiation and agreement frameworks that foster cooperation, allow all agents to meet their individual policy objectives, and incentivize long-term adherence. This is an interdisciplinary challenge that calls for collaboration between researchers in machine learning, economics, climate science, law, policy, ethics, and other fields. In particular, we argue that machine learning is a critical tool to address the complexity of this domain. To facilitate this research, here we introduce RICE-N, a multi-region integrated assessment model that simulates the global climate and economy, and which can be used to design and evaluate the strategic outcomes for different negotiation and agreement frameworks. We also describe how to use multi-agent reinforcement learning to train rational agents using RICE-N. This framework underpinsAI for Global Climate Cooperation, a working group collaboration and competition on climate negotiation and agreement design. Here, we invite the scientific community to design and evaluate their solutions using RICE-N, machine learning, economic intuition, and other domain knowledge. More information can be found on www.ai4climatecoop.org.

Robust decision-making in multiplayer games requires anticipating what reactions a player policy may elicit from other players. This is diffi-cult in games with three or more players: when one player fixes a policy, it induces a subgame between the remaining players with many possible equilibria outcomes. Predicting the worst-case outcome of a policy is thus an equilibrium selection problem—one known to be generally NP-Hard. We show that worst-case coarse-correlated equilibria can be efficiently approxi-mated in smooth games and propose a framework that uses the worst-case evaluation scheme to learn robust player policies. We further prove the framework can be extended to handle uncertainty about the bounded rationality of other players. In experiments, our framework learns robust policies in repeated N -player matrix games and, when applied to deep multi-agent reinforcement learning, can scale to complex spatiotemporal games. For example, it learns robust AI tax policies that improve welfare by up to 15%, even when taxpayers are boundedly rational. and ‘AI Economist (Original)’ are trained on the ‘Original’ settings (risk aversion η 0 23 entropy bonus α = 0 . 025 ). Naive multi-agent reinforcement learning tax policies, including (Zheng et al., 2020)’s original AI Economist, fail to generalize to previously unseen agent types. In contrast, our algorithm performs within standard error of top-1 on all agent types.

Real economies can be seen as a sequential imperfect-information game with many heterogeneous, interacting strategic agents of various agent types, such as consumers, firms, and governments. Dynamic general equilibrium models are common economic tools to model the economic activity, interactions, and outcomes in such systems. However, existing analytical and computational methods struggle to find explicit equilibria when all agents are strategic and interact, while joint learning is unstable and challenging. Amongst others, a key reason is that the actions of one economic agent may change the reward function of another agent, e.g., a consumer's expendable income changes when firms change prices or governments change taxes. We show that multi-agent deep reinforcement learning (RL) can discover stable solutions that are $\epsilon$-Nash equilibria for a meta-game over agent types, in economic simulations with many agents, through the use of structured learning curricula and efficient GPU-only simulation and training.Conceptually, our approach is more flexible and does not need unrealistic assumptions, e.g., market clearing, that are commonly used for analytical tractability. Our GPU implementation enables training and analyzing economies with a large number of agents within reasonable time frames, e.g., training completes within a day. We demonstrate our approach in real-business-cycle models, a representative family of DGE models, with 100 worker-consumers, 10 firms, and a government who taxes and redistributes. We validate the learned meta-game $\epsilon$-Nash equilibria through approximate best-response analyses, show that RL policies align with economic intuitions, and that our approach is constructive, e.g., by explicitly learning a spectrum of meta-game $\epsilon$-Nash equilibria in open economic models.

Real economies can be modeled as a sequential imperfect-information game with many heterogeneous agents, such as consumers, firms, and governments. Dynamic general equilibrium (DGE) models are often used for macroeconomic analysis in this setting. However, finding general equilibria is challenging using existing theoretical or computational methods, especially when using microfoundations to model individual agents. Here, we show how to use deep multi-agent reinforcement learning (MARL) to find $\epsilon$-meta-equilibria over agent types in microfounded DGE models. Whereas standard MARL fails to learn non-trivial solutions, our structured learning curricula enable stable convergence to meaningful solutions. Conceptually, our approach is more flexible and does not need unrealistic assumptions, e.g., continuous market clearing, that are commonly used for analytical tractability. Furthermore, our end-to-end GPU implementation enables fast real-time convergence with a large number of RL economic agents. We showcase our approach in open and closed real-business-cycle (RBC) models with 100 worker-consumers, 10 firms, and a social planner who taxes and redistributes. We validate the learned solutions are $\epsilon$-meta-equilibria through best-response analyses, show that they align with economic intuitions, and show our approach can learn a spectrum of qualitatively distinct $\epsilon$-meta-equilibria in open RBC models. As such, we show that hardware-accelerated MARL is a promising framework for modeling the complexity of economies based on microfoundations.

WarpDrive is a flexible, lightweight, and easy-to-use open-source framework for end-to-end deep multi-agent reinforcement learning (MARL) on a Graphics Processing Unit (GPU), available at https://github.com/salesforce/warp-drive . It addresses key system bot-tlenecks when applying MARL to complex environments with high-dimensional state, ob-servation, or action spaces. For example, WarpDrive eliminates data copying between the CPU and GPU and runs thousands of simulations and agents in parallel. It also enables distributed training on multiple GPUs and scales to millions of agents. In all, WarpDrive enables orders-of-magnitude faster MARL compared to common CPU-GPU implementations. For example, WarpDrive yields 2.9 million environment steps/second with 2000 environments and 1000 agents (at least 100 × faster than a CPU version) in a 2d-Tag simulation. It is user-friendly: e.g., it provides a lightweight, extendable Python interface and flexible environment wrappers. It is also compatible with PyTorch. In all, WarpDrive offers a platform to significantly accelerate reinforcement learning research and development.

Principal-Agent (PA) problems describe a broad class of economic relationships characterized by misaligned incentives and asymmetric information. The Principal's problem is to find optimal incentives given the available information, e.g., a manager setting optimal wages for its employees. Whereas the Principal is often assumed rational, comparatively little is known about solutions when the Principal is boundedly rational, especially in the sequential setting, with multiple Agents, and with multiple information channels. Here, we develop RIRL, a deep reinforcement learning framework that solves such complex PA problems with a rationally inattentive Principal. Such a Principal incurs a cost for paying attention to information, which can model forms of bounded rationality. We use RIRL to analyze rich economic phenomena in manager-employee relationships. In the single-step setting, 1) RIRL yields wages that are consistent with theoretical predictions; and 2) non-zero attention costs lead to simpler but less profitable wage structures, and increased Agent welfare. In a sequential setting with multiple Agents, RIRL shows opposing consequences of the Principal's inattention to different information channels: 1) inattention to Agents' outputs closes wage gaps based on ability differences; and 2) inattention to Agents' efforts induces a social dilemma dynamic in which Agents work harder, but essentially for free. Moreover, RIRL reveals non-trivial relationships between the Principal's inattention and Agent types, e.g., if Agents are prone to sub-optimal effort choices, payment schedules are more sensitive to the Principal's attention cost. As such, RIRL can reveal novel economic relationships and enables progress towards understanding the effects of bounded rationality in dynamic settings.

Artificial intelligence (AI) and reinforcement learning (RL) have improved many areas but are not yet widely adopted in economic policy design, mechanism design, or economics at large. The AI Economist is a two-level, deep RL framework for policy design in which agents and a social planner coadapt. In particular, the AI Economist uses structured curriculum learning to stabilize the challenging two-level, coadaptive learning problem. We validate this framework in the domain of taxation. In one-step economies, the AI Economist recovers the optimal tax policy of economic theory. In spatiotemporal economies, the AI Economist substantially improves both utilitarian social welfare and the trade-off between equality and productivity over baselines. It does so despite emergent tax-gaming strategies while accounting for emergent labor specialization, agent interactions, and behavioral change. These results demonstrate that two-level, deep RL complements economic theory and unlocks an AI-based approach to designing and understanding economic policy.

The development and deployment of machine learning (ML) systems can be executed easily with modern tools, but the process is typically rushed and means-to-an-end. The lack of diligence can lead to technical debt, scope creep and misaligned objectives, model misuse and failures, and expensive consequences. Engineering systems, on the other hand, follow well-defined processes and testing standards to streamline development for high-quality, reliable results. The extreme is spacecraft systems, where mission critical measures and robustness are ingrained in the development process. Drawing on experience in both spacecraft engineering and ML (from research through product across domain areas), we have developed a proven systems engineering approach for machine learning development and deployment. Our "Machine Learning Technology Readiness Levels" (MLTRL) framework defines a principled process to ensure robust, reliable, and responsible systems while being streamlined for ML workflows, including key distinctions from traditional software engineering. Even more, MLTRL defines a lingua franca for people across teams and organizations to work collaboratively on artificial intelligence and machine learning technologies. Here we describe the framework and elucidate it with several real world use-cases of developing ML methods from basic research through productization and deployment, in areas such as medical diagnostics, consumer computer vision, satellite imagery, and particle physics.

Policies for real-world multi-agent problems, such as optimal taxation, can be learned in multi-agent simulations with AI agents that emulate humans. However, simulations can suffer from reality gaps as humans often act suboptimally or optimize for different objectives (i.e., bounded rationality). We introduce $\epsilon$-Robust Multi-Agent Simulation (ERMAS), a robust optimization framework to learn AI policies that are robust to such multi-agent reality gaps. The objective of ERMAS theoretically guarantees robustness to the $\epsilon$-Nash equilibria of other agents – that is, robustness to behavioral deviations with a regret of at most $\epsilon$. ERMAS efficiently solves a first-order approximation of the robustness objective using meta-learning methods. We show that ERMAS yields robust policies for repeated bimatrix games and optimal adaptive taxation in economic simulations, even when baseline notions of robustness are uninformative or intractable. In particular, we show ERMAS can learn tax policies that are robust to changes in agent risk aversion, improving policy objectives (social welfare) by up to 15% in complex spatiotemporal simulations using the AI Economist (Zheng et al., 2020).

Multi-agent simulations provide a scalable environment for learning policies that interact with rational agents. However, such policies may fail to generalize to the real-world where agents may differ from simulated counterparts due to unmodeled irrationality and misspecified reward functions. We introduce Epsilon-Robust Multi-Agent Simulation (ERMAS), a robust optimization framework for learning AI policies that are robust to such multiagent sim-to-real gaps. While existing notions of multi-agent robustness concern perturbations in the actions of agents, we address a novel robustness objective concerning perturbations in the reward functions of agents. ERMAS provides this robustness by anticipating suboptimal behaviors from other agents, formalized as the worst-case epsilon-equilibrium. We show empirically that ERMAS yields robust policies for repeated bimatrix games and optimal taxation problems in economic simulations. In particular, in the two-level RL problem posed by the AI Economist (Zheng et al., 2020) ERMAS learns tax policies that are robust to changes in agent risk aversion, improving social welfare by up to 15% in complex spatiotemporal simulations.

Optimizing economic and public policy is critical to address socioeconomic issues and trade-offs, e.g., improving equality, productivity, or wellness, and poses a complex mechanism design problem. A policy designer needs to consider multiple objectives, policy levers, and behavioral responses from strategic actors who optimize for their individual objectives. Moreover, real-world policies should be explainable and robust to simulation-to-reality gaps, e.g., due to calibration issues. Existing approaches are often limited to a narrow set of policy levers or objectives that are hard to measure, do not yield explicit optimal policies, or do not consider strategic behavior, for example. Hence, it remains challenging to optimize policy in real-world scenarios. Here we show that the AI Economist framework enables effective, flexible, and interpretable policy design using two-level reinforcement learning (RL) and data-driven simulations. We validate our framework on optimizing the stringency of US state policies and Federal subsidies during a pandemic, e.g., COVID-19, using a simulation fitted to real data. We find that log-linear policies trained using RL significantly improve social welfare, based on both public health and economic outcomes, compared to past outcomes. Their behavior can be explained, e.g., well-performing policies respond strongly to changes in recovery and vaccination rates. They are also robust to calibration errors, e.g., infection rates that are over or underestimated. As of yet, real-world policymaking has not seen adoption of machine learning methods at large, including RL and AI-driven simulations. Our results show the potential of AI to guide policy design and improve social welfare amidst the complexity of the real world.