Multi-Agent Reinforcement Learning involves agents that learn together in a shared environment, leading to emergent dynamics sensitive to initial conditions and parameter variations. A Dynamical Systems approach, which studies the evolution of multi-component systems over time, has uncovered some of the underlying dynamics by constructing deterministic approximation models of stochastic algorithms. In this work, we demonstrate that even in the simplest case of independent Q-learning with a Boltzmann exploration policy, significant discrepancies arise between the actual algorithm and previous approximations. We elaborate why these models actually approximate interesting variants rather than the original incremental algorithm. To explain the discrepancies, we introduce a new discrete-time approximation model that explicitly accounts for agents' update frequencies within the learning process and show that its dynamics fundamentally differ from the simplified dynamics of prior models. We illustrate the usefulness of our approach by applying it to the question of spontaneous cooperation in social dilemmas, specifically the Prisoner's Dilemma as the simplest case study. We identify conditions under which the learning behaviour appears as long-term stable cooperation from an external perspective. However, our model shows that this behaviour is merely a metastable transient phase and not a true equilibrium, making it exploitable. We further exemplify how specific parameter settings can significantly exacerbate the moving target problem in independent learning. Through a systematic analysis of our model, we show that increasing the discount factor induces oscillations, preventing convergence to a joint policy. These oscillations arise from a supercritical Neimark-Sacker bifurcation, which transforms the unique stable fixed point into an unstable focus surrounded by a stable limit cycle.

Foundation models such as GPT-4 are fine-tuned to avoid unsafe or otherwise problematic behavior, such as helping to commit crimes or producing racist text. One approach to fine-tuning, called reinforcement learning from human feedback, learns from humans' expressed preferences over multiple outputs. Another approach is constitutional AI, in which the input from humans is a list of high-level principles. But how do we deal with potentially diverging input from humans? How can we aggregate the input into consistent data about "collective" preferences or otherwise use it to make collective choices about model behavior? In this paper, we argue that the field of social choice is well positioned to address these questions, and we discuss ways forward for this agenda, drawing on discussions in a recent workshop on Social Choice for AI Ethics and Safety held in Berkeley, CA, USA in December 2023.

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.

The Paris Agreement, considered a significant milestone in climate negotiations, has faced challenges in effectively addressing climate change due to the unconditional nature of most Nationally Determined Contributions (NDCs). This has resulted in a prevalence of free-riding behavior among major polluters and a lack of concrete conditionality in NDCs. To address this issue, we propose the implementation of a decentralized, bottom-up approach called the Conditional Commitment Mechanism. This mechanism, inspired by the National Popular Vote Interstate Compact, offers flexibility and incentives for early adopters, aiming to formalize conditional cooperation in international climate policy. In this paper, we provide an overview of the mechanism, its performance in the AI4ClimateCooperation challenge, and discuss potential real-world implementation aspects. Prior knowledge of the climate mitigation collective action problem, basic economic principles, and game theory concepts are assumed.

Many real-world situations of ethical relevance, in particular those of large-scale social choice such as mitigating climate change, involve not only many agents whose decisions interact in complicated ways, but also various forms of uncertainty, including quantifiable risk and unquantifiable ambiguity. In such problems, an assessment of individual and groupwise moral responsibility for ethically undesired outcomes or their responsibility to avoid such is challenging and prone to the risk of under- or overdetermination of responsibility. In contrast to existing approaches based on strict causation or certain deontic logics that focus on a binary classification of `responsible' vs `not responsible', we here present several different quantitative responsibility metrics that assess responsibility degrees in units of probability. For this, we use a framework based on an adapted version of extensive-form game trees and an axiomatic approach that specifies a number of potentially desirable properties of such metrics, and then test the developed candidate metrics by their application to a number of paradigmatic social choice situations. We find that while most properties one might desire of such responsibility metrics can be fulfilled by some variant, an optimal metric that clearly outperforms others has yet to be found.