paper-with-me

홈 › Papers

Skill Characterization Based on Betweenness

2008-12-01 · NeurIPS 2008 12 · Özgür Şimşek, Andrew G. Barto

We present a characterization of a useful class of skills based on a graphical representation of an agent's interaction with its environment. Our characterization uses betweenness, a measure of centrality on graphs. It may be used directly to form a set of skills suitable for a given environment. More importantly, it serves as a useful guide for developing online, incremental skill discovery algorithms that do not rely on knowing or representing the environment graph in its entirety.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Finite Tests from Functional Characterizations

2022-08-07 · Charles Gauthier, Raghav Malhotra, Agustin Troccoli Moretti

Classically, testing whether decision makers belong to specific preference classes involves two main approaches. The first, known as the functional approach, assumes access to an entire demand function. The second, the r…

ONBRA: Rigorous Estimation of the Temporal Betweenness Centrality in Temporal Networks

2022-03-01 · Diego Santoro, Ilie Sarpe

In network analysis, the betweenness centrality of a node informally captures the fraction of shortest paths visiting that node. The computation of the betweenness centrality measure is a fundamental task in the analysis…

Monotone additive statistics

2021-02-01 · Xiaosheng Mu, Luciano Pomatto, Philipp Strack, Omer Tamuz

The expectation is an example of a descriptive statistic that is monotone with respect to stochastic dominance, and additive for sums of independent random variables. We provide a complete characterization of such statis…

Decision MakingDescriptive

A simple proof of the representation theorem for betweenness preferences

2024-05-18 · Yutaro Akita

This paper presents a simple proof of Dekel (1986)'s representation theorem for betweenness preferences. The proof is based on the separation theorem.

When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions

2024-06-12 · Zhening Li, Gabriel Poesia, Armando Solar-Lezama

Skills are temporal abstractions that are intended to improve reinforcement learning (RL) performance through hierarchical RL. Despite our intuition about the properties of an environment that make skills useful, a preci…

Reinforcement Learning (RL)