This paper introduces Diffusion Policy, a new way of generating robot behavior by representing a robot’s visuomotor policy as a conditional denoising diffusion process. We benchmark Diffusion Policy across 15 different tasks from 4 different robot manipulation benchmarks and find that it consistently outperforms existing state-of-the-art robot learning methods with an average improvement of 46.9%. Diffusion Policy learns the gradient of the action-distribution score function and iteratively optimizes with respect to this gradient field during inference via a series of stochastic Langevin dynamics steps. We find that the diffusion formulation yields powerful advantages when used for robot policies, including gracefully handling multimodal action distributions, being suitable for high-dimensional action spaces, and exhibiting impressive training stability. To fully unlock the potential of diffusion models for visuomotor policy learning on physical robots, this paper presents a set of key technical contributions including the incorporation of receding horizon control, visual conditioning, and the time-series diffusion transformer. We hope this work will help motivate a new generation of policy learning techniques that are able to leverage the powerful generative modeling capabilities of diffusion models. Code, data, and training details are available (diffusion-policy.cs.columbia.edu).
Despite its rich tradition, there are key limitations to researchers' ability to make generalizable inferences about state policy innovation and diffusion. This paper introduces new data and methods to move from empirical analyses of single policies to the analysis of comprehensive populations of policies and rigorously inferred diffusion networks. We have gathered policy adoption data appropriate for estimating policy innovativeness and tracing diffusion ties in a targeted manner (e.g., by policy domain, time period, or policy type) and extended the development of methods necessary to accurately and efficiently infer those ties. Our state policy innovation and diffusion (SPID) database includes 728 different policies coded by topic area. We provide an overview of this new dataset and illustrate two key uses: (i) static and dynamic innovativeness measures and (ii) latent diffusion networks that capture common pathways of diffusion between states across policies. The scope of the data allows us to compare patterns in both across policy topic areas. We conclude that these new resources will enable researchers to empirically investigate classes of questions that were difficult or impossible to study previously, but whose roots go back to the origins of the political science policy innovation and diffusion literature.
more » « less- PAR ID:
- 10457799
- Publisher / Repository:
- Wiley-Blackwell
- Date Published:
- Journal Name:
- Policy Studies Journal
- Volume:
- 48
- Issue:
- 2
- ISSN:
- 0190-292X
- Page Range / eLocation ID:
- p. 517-545
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
-
Well-resourced and well-connected individuals, or “policy entrepreneurs,” often play an important role in advocating and securing the adoption of policies. There is a striking lack of inquiry into the ways that social networks shape the ability of these actors to achieve their aims, including the ways in which network ties may channel policy conflict. To address these gaps, we analyze data from an original survey and an original database of policies to assess the success of policy entrepreneurs active in a highly contentious arena: municipal policymaking concerning high-volume hydraulic fracturing (HVHF) in New York. We use text-mining to collect social network data from local newspaper archives, then use those data to construct municipal HVHF policy networks. Municipal anti-HVHF policy entrepreneurs appear more successful when they operate in less cohesive networks, act as bridges to relative newcomers to the governance network, and have a larger number of network connections. Pro-HVHF policy entrepreneurs appear more successful when they can forge high-value connections to key decision-makers. Policy entrepreneurs on both sides of the issue are more successful when they have a greater number of sympathetic coalition partners.more » « less
-
more » « less
Abstract Sub‐national governments across the United States implement a variety of policies to address large societal problems and needs. Many policies are picked up or adopted in other states. This process is called policy diffusion and allows researchers to analyse and compare the social, political, and contextual characteristics that lead to adopting certain policies, as well as the efficacy of these policies once adopted. In this paper, we introduce PDViz, a visual analytics approach that allows social scientists to dynamically analyse the policy diffusion history and underlying patterns. It is designed for analysing and answering a list of research questions and tasks posed by social scientists in prior work. To evaluate our system, we present two usage scenarios and conduct interviews with domain experts in political science. The interviews highlight that PDViz provides the result of policy diffusion patterns that align with their domain knowledge as well as the potential to be a learning tool for students to understand the concept of policy diffusion.
-
more » « less
Abstract Despite the reality that advocates frequently expend significant resources to pass symbolic policies, this policy design has often been neglected by policy studies scholarship. We combine policy design and policy feedback theory to examine this oft overlooked policy design in practice using the case of California's human right to water law (Assembly Bill 685, or AB 685). Through semi‐structured interviews, archival research, and document analysis, we reveal how grassroots advocates deliberately and effectively pursued AB 685 to build power across the water justice movement and catalyze narrative change about drinking water access, while also building state responsiveness on the topic. These interpretive policy feedback effects then accelerated the policy's resource effects through formal policy changes in funding allocations, administrative structures, and regulatory systems. Collectively, feedbacks from AB 685 have transformed the sociopolitics of drinking water access. Contrary to prevailing wisdom, the policy's ambiguity proved key to building the broad coalition necessary to accomplish these changes, and it facilitated work across policy venues and governance scales through time, which is critical to enacting transformational change. Based on these findings, we argue that symbolic policies merit attention as a potentially advantageous policy design for social movements seeking social change and transformation.
-
Policy information in computer networking today, such as reachability objectives of a controller program running on a Software Defined Network (henceforth referred to as SDN) or Border Gateway Protocol (henceforth referred to as BGP) configurations independently set by autonomous networks, are hard to manage. This is in sharp contrast to the relational data structured in a database that allows easy access. This paper asks why cannot (or how can) we turn network policies into relational data. One difficulty to such an approach is that a policy does not always translate to a \textit{definite} network snapshot, but rather is fully described only when we include all the possible network states it admits. We propose relational policies that, while capable of representing and manipulating sets of network states in exactly the same way as a single one, form a strong representation system and accurately capture the information in a policy with the usual Structured Query Language (henceforth referred to as SQL) interface. We demonstrate how, like relational database improves application productivity and enables rapid innovation, relational policies allow us to extend the elegant solutions that the database community developed, to mediate multiple data sources in order to address long-standing challenges and new opportunities for autonomous policy making in the distributed networking environment. We also show the feasibility of relational policies by evaluation on synthetic policies and realistic network topologies.more » « less
