ML4EJ: Decoding the Role of Urban Features in Shaping Environmental Injustice Using Interpretable Machine Learning [PDF]
Understanding the key factors shaping environmental hazard exposures and their associated environmental injustice issues is vital for formulating equitable policy measures. Traditional perspectives on environmental injustice have primarily focused on the socioeconomic dimensions, often overlooking the influence of heterogeneous urban characteristics ...
arxiv
Scaling laws in global corporations as a benchmarking approach to assess environmental performance [PDF]
The largest 6,529 international corporations are accountable for almost 30% of global CO2e emissions. A growing awareness of the role of the corporate world in the path toward sustainability has led many shareholders and stakeholders to pursue increasingly stringent and ambitious environmental goals.
arxiv
Uncertainty Aware System Identification with Universal Policies [PDF]
Sim2real transfer is primarily concerned with transferring policies trained in simulation to potentially noisy real world environments. A common problem associated with sim2real transfer is estimating the real-world environmental parameters to ground the simulated environment to.
arxiv
The Unintended Carbon Consequences of Bitcoin Mining Bans: A Paradox in Environmental Policy [PDF]
The environmental impact of Bitcoin mining has become a significant concern, prompting several governments to consider or implement bans on cryptocurrency mining. However, these well-intentioned policies may lead to unintended consequences, notably the redirection of mining activities to regions with higher carbon intensities.
arxiv
Public Support for Environmental Regulation: When Ideology Trumps Knowledge [PDF]
When environmental regulations are unpopular, policymakers often attribute resistance to information frictions and poor communication. We test this idea in the context of a major climate policy: Germany's Heating Law of 2023, which mandates the phase-out of fossil fuel heating.
arxiv
Agent Probing Interaction Policies [PDF]
Reinforcement learning in a multi agent system is difficult because these systems are inherently non-stationary in nature. In such a case, identifying the type of the opposite agent is crucial and can help us address this non-stationary environment. We have investigated if we can employ some probing policies which help us better identify the type of ...
arxiv
Efficient Data Collection for Robotic Manipulation via Compositional Generalization [PDF]
Data collection has become an increasingly important problem in robotic manipulation, yet there still lacks much understanding of how to effectively collect data to facilitate broad generalization. Recent works on large-scale robotic data collection typically vary many environmental factors of variation (e.g., object types, table textures) during data ...
arxiv
Towards A Comprehensive Assessment of AI's Environmental Impact [PDF]
Artificial Intelligence, machine learning (AI/ML) has allowed exploring solutions for a variety of environmental and climate questions ranging from natural disasters, greenhouse gas emission, monitoring biodiversity, agriculture, to weather and climate modeling, enabling progress towards climate change mitigation. However, the intersection of AI/ML and
arxiv
Environmental policies as a pull factor for tourists? Insights from Italy [PDF]
Tourism consumption has grown into a major economic factor for modern societies. However, the environmental impact of tourism has become a significant concern, leading to an increased focus on sustainable tourism policies. While governments and institutions have introduced frameworks to promote ecological transition in the tourism sector, the ...
arxiv
Environmental Policy in General Equilibrium under Market Power and Price Discrimination [PDF]
This study constructs a novel analytical general equilibrium model to compare environmental policies in a setting where oligopolistic energy firms engage in third-degree price discrimination across residential consumers and industrial firms. Closed-form solutions demonstrate the impact on prices and quantities.
arxiv