Inference of Unknown Dynamical Components Using Next Generation Reservoir Computing: From Chaotic Systems to Climate Data
本文使用下一代水库计算(NGRC)方法从已知部分推断动力系统的未知成分，相比传统方法，它需要更少的数据和时间，并在混沌系统及气候数据上验证了其有效性。
0 citationsRead paper
Selected work
Representative Papers
Does the grand coalition form? Persistence, arrival, and the role of the sharing rule in a dynamic process of nested binding agreements
研究动态联盟形成过程，通过分析折扣长期预期收益和自确认信念，探讨了大联盟形成的条件及其吸收状态。
0 citationsRead paper
A Fair Objective for Human-Empowerment-Preserving AI: Desiderata, Design, and Likely Behavioral Consequences
This work proposes a parametric and decomposable AI objective function designed to safeguard human well-being and safety while maintaining an equitable balance of power in human–AI interaction. The function aggregates human utilities with explicit consideration for long-term outcomes, risk aversion, and disparities in human capabilities, integrating models of bounded rationality and social norms to accommodate diverse human goals. Grounded in axiomatic design principles, it explicitly enshrines human empowerment and power balance as core desiderata, yielding a functional form and associated parameter constraints that satisfy desirable theoretical properties. Theoretical analysis and case studies demonstrate that the proposed objective effectively achieves soft maximization of human utility and reveals emergent instrumental subgoals and behavioral implications inherent to its structure.
0 citationsRead paper
Planning resilient hydrogen supply chains under disruption risk
This study addresses the critical oversight in existing green hydrogen supply chain planning—the neglect of supply disruption risks, which can lead to substantial welfare losses and systemic vulnerability. To mitigate these issues, the authors propose a risk-aware stochastic optimization model tailored to the European Union’s hydrogen import system, integrating two complementary resilience strategies: diversification of import corridors and strategic overinvestment in infrastructure. The framework holistically evaluates infrastructure configurations and their economic impacts across a range of disruption scenarios. Compared to conventional risk-agnostic planning approaches, the proposed model reduces welfare losses by 12% (approximately €24 billion), achieves performance nearly equivalent to that of an idealized disruption-free system, and yields significantly improved transport network design and terminal deployment.
0 citationsRead paper
Model-Based Soft Maximization of Suitable Metrics of Long-Term Human Power
This paper addresses the fundamental tension between AI safety and human welfare by redefining the optimization objective around “human power” — a normative construct capturing agency, autonomy, and collective capability. Method: We propose an axiomatic framework featuring a parameterized, decomposable objective function that explicitly encodes long-horizon considerations, inequality sensitivity, and risk aversion in aggregating human power. The model integrates bounded rationality, social norms, and multi-objective preferences to enable adaptive power balancing under dynamic conditions. Optimization employs backward induction combined with world-model-based multi-agent reinforcement learning for tractable approximation. Contribution/Results: By substituting soft maximization of human power for conventional utility maximization, our approach mitigates instrumental convergence risks. Experiments across canonical scenarios demonstrate that the framework consistently induces AI systems to generate beneficial instrumental subgoals, yielding substantial improvements in system safety and human–AI collaboration efficacy.
0 citationsRead paper
Recent publications
Latest Papers
Inference of Unknown Dynamical Components Using Next Generation Reservoir Computing: From Chaotic Systems to Climate Data
本文使用下一代水库计算(NGRC)方法从已知部分推断动力系统的未知成分，相比传统方法，它需要更少的数据和时间，并在混沌系统及气候数据上验证了其有效性。
0 citationsRead paper
Does the grand coalition form? Persistence, arrival, and the role of the sharing rule in a dynamic process of nested binding agreements
研究动态联盟形成过程，通过分析折扣长期预期收益和自确认信念，探讨了大联盟形成的条件及其吸收状态。
0 citationsRead paper
A Fair Objective for Human-Empowerment-Preserving AI: Desiderata, Design, and Likely Behavioral Consequences
This work proposes a parametric and decomposable AI objective function designed to safeguard human well-being and safety while maintaining an equitable balance of power in human–AI interaction. The function aggregates human utilities with explicit consideration for long-term outcomes, risk aversion, and disparities in human capabilities, integrating models of bounded rationality and social norms to accommodate diverse human goals. Grounded in axiomatic design principles, it explicitly enshrines human empowerment and power balance as core desiderata, yielding a functional form and associated parameter constraints that satisfy desirable theoretical properties. Theoretical analysis and case studies demonstrate that the proposed objective effectively achieves soft maximization of human utility and reveals emergent instrumental subgoals and behavioral implications inherent to its structure.
0 citationsRead paper
Planning resilient hydrogen supply chains under disruption risk
This study addresses the critical oversight in existing green hydrogen supply chain planning—the neglect of supply disruption risks, which can lead to substantial welfare losses and systemic vulnerability. To mitigate these issues, the authors propose a risk-aware stochastic optimization model tailored to the European Union’s hydrogen import system, integrating two complementary resilience strategies: diversification of import corridors and strategic overinvestment in infrastructure. The framework holistically evaluates infrastructure configurations and their economic impacts across a range of disruption scenarios. Compared to conventional risk-agnostic planning approaches, the proposed model reduces welfare losses by 12% (approximately €24 billion), achieves performance nearly equivalent to that of an idealized disruption-free system, and yields significantly improved transport network design and terminal deployment.
0 citationsRead paper
Model-Based Soft Maximization of Suitable Metrics of Long-Term Human Power
This paper addresses the fundamental tension between AI safety and human welfare by redefining the optimization objective around “human power” — a normative construct capturing agency, autonomy, and collective capability. Method: We propose an axiomatic framework featuring a parameterized, decomposable objective function that explicitly encodes long-horizon considerations, inequality sensitivity, and risk aversion in aggregating human power. The model integrates bounded rationality, social norms, and multi-objective preferences to enable adaptive power balancing under dynamic conditions. Optimization employs backward induction combined with world-model-based multi-agent reinforcement learning for tractable approximation. Contribution/Results: By substituting soft maximization of human power for conventional utility maximization, our approach mitigates instrumental convergence risks. Experiments across canonical scenarios demonstrate that the framework consistently induces AI systems to generate beneficial instrumental subgoals, yielding substantial improvements in system safety and human–AI collaboration efficacy.
0 citationsRead paper