A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
Options of Interest: Temporal Abstraction with Interest Functions
[article]
2020
arXiv
pre-print
We provide a generalization of initiation sets suitable for general function approximation, by defining an interest function associated with an option. ...
We investigate how interest functions can be leveraged to learn interpretable and reusable temporal abstractions. ...
Options learned with interest functions emerge with specific interest in different regions of the state. tion (0.3, 0. ...
arXiv:2001.00271v1
fatcat:2rbfbzj45fbbrg3dspitvx5rve
Options of Interest: Temporal Abstraction with Interest Functions
2020
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
We provide a generalization of initiation sets suitable for general function approximation, by defining an interest function associated with an option. ...
We investigate how interest functions can be leveraged to learn interpretable and reusable temporal abstractions. ...
Constructing such temporal abstractions automatically from data has also been tackled extensively, and with some success (Konidaris et al. 2011; Figure 6 : Timeline of options used by IOC agent in HalfCheetah ...
doi:10.1609/aaai.v34i04.5871
fatcat:ysrw5ciqzrdt7h3ghdiwnd7vi4
Learning Options with Interest Functions
2019
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
We aim to autonomously learn options which are specialized in different state space regions by proposing a notion of interest functions, which generalizes initiation sets from the options framework for ...
We build on the option-critic framework to derive policy gradient theorems for interest functions, leading to a new interest-option-critic architecture. ...
Given a set of Markov options with stochastic, differentiable interest functions I ω,z , the gradient of the expected discounted return with respect to z at (s, ω) is: s ,ω μ Ω (s , ω |s, ω)β ω,ν (s ) ...
doi:10.1609/aaai.v33i01.33019955
fatcat:2oqhexjjerbvrcy6hqscooh2t4
What Is Interesting? Exploring the Appraisal Structure of Interest
2005
Emotion
option. ...
Correlations between appraisals of ability and interest as a function of stimulus complexity: Experiment 3. ...
doi:10.1037/1528-3542.5.1.89
pmid:15755222
fatcat:7lbgqzdry5emdj2qib442qmlfe
Cryonics in the Courtroom: Which Interests? Whose Interests?
2017
Medical Law Review
Starting with autonomy interests, the judgment implicitly supported a relational account of autonomy, but was dominated by a subjective interpretation of autonomy, which prioritized JS's wishes. ...
Temporal concerns also feature when we interpret welfare in terms of happiness, because the dying person and the (potential) future reanimated person might have different interests at different times. ...
In addition to the temporal dilemmas associated with the current and future interests of individual patients, questions arise about whose interests should be in issue, whether current or future. ...
doi:10.1093/medlaw/fwx045
pmid:29077877
pmcid:PMC6093470
fatcat:nzzwvggmyfbgvcsy4b4a23aqym
Profiling interest relativity
2008
Analysis
Stanley's claims about the epistemological profile of interest-relative propositions are incorrect. His claims about the modal profile of interest-relative propositions are correct, but not worrisome. ...
Here I rebut a two-part objection to my interest-relative theory of vagueness in both of these ways. 1 The objection, as developed by Jason Stanley (2003, 2005), concerns the modal and epistemological ...
This function will of course vary with the adjective in the sentence; when the adjective is 'tall', f (C) is the normal height for C. ...
doi:10.1111/j.1467-8284.2008.00761.x
fatcat:ulw23rr7p5dfjfu3pvgq6bevku
On the Role of Weight Sharing During Deep Option Learning
2020
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
We thus reconsider this assumption and consider more general extensions of option-critic and hierarchical option-critic training that optimize for the full architecture with each update. ...
In this work we note that while this key assumption of the policy gradient theorems of option-critic holds in the tabular case, it is always violated in practice for the deep function approximation setting ...
arbitrarily deep option hierarchy with N levels of abstraction. ...
doi:10.1609/aaai.v34i04.6003
fatcat:wnr4rtt3xzghpmd65njup7res4
Common Interest Tragedies
2003
Social Science Research Network
In subpart C, I show how the heterogeneity among production functions associated with the assembly of fragmentary interests provides a meaningful way of weighing these options. ...
The first Part lays the groundwork for dividing up the universe of common interest tragedies functionally. ...
However, it is a quite important corner, and the light that the analysis sheds demonstrates the payoff of this Article's taxonomy of common interest tragedies. ...
doi:10.2139/ssrn.474380
fatcat:i74tvec3bjdqveewqbwc3fco7u
User Interests Identification on Twitter Using a Hierarchical Knowledge Base
[chapter]
2014
Lecture Notes in Computer Science
We argue that the hierarchical semantics of concepts can enhance existing systems to personalize or recommend items based on a varied level of conceptual abstractness. ...
Semantic enrichment of Twitter posts, to determine user interests, has been an active area of research in the recent past. ...
Further, we want to include temporal aspect to score interests where recently mentioned interests are scored higher. ...
doi:10.1007/978-3-319-07443-6_8
fatcat:v57lgrxgl5g6tku67plcflinhy
Your Online Interests
2014
Proceedings of the 2014 ACM SIGSAC Conference on Computer and Communications Security - CCS '14
The attack is robust to diverse browsing patterns and online interests of users. ...
We validate the attack for one of the largest ad exchanges and empirically measure the monetary gains of the publisher by emulating the attack using web traces of 619 real users. ...
Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. ...
doi:10.1145/2660267.2687258
dblp:conf/ccs/MengXSWL14
fatcat:36ruvs6tszcwhdlxlwgfd6ewky
Inferring user interests in microblogging social networks: a survey
2018
User modeling and user-adapted interaction
Through this survey, we aim to provide an overview of state-of-the-art user modeling strategies for inferring user interest profiles on microblogging social networks with respect to the four dimensions ...
To this end, we focus on four dimensions of inferring user interest profiles: (1) data collection, (2) representation of user interest profiles, (3) construction and enhancement of user interest profiles ...
the financial support of Science Foundation Ireland (SFI) under Grant Number SFI/12/RC/2289 (Insight Centre for Data Analytics). ...
doi:10.1007/s11257-018-9207-8
fatcat:yyvertb3jfdhzc4oaxsgnimznu
The Econometrics of Option Pricing
[chapter]
2010
Handbook of Financial Econometrics: Tools and Techniques
each with their own bandwidth value, with respect to the three variables of interest, and where ¾ i is the Black-Scholes volatility implied by the observed price of option i: A call pricing function can ...
Third, we will survey the purely nonparametric approaches such as kerned-based techniques or learning networks used to estimate an option pricing function and recover the other quantities of interest with ...
doi:10.1016/b978-0-444-50897-3.50012-2
fatcat:oyzapebuynbjvfgwc5aefkohtq
The Econometrics of Option Pricing
2003
Social Science Research Network
each with their own bandwidth value, with respect to the three variables of interest, and where ¾ i is the Black-Scholes volatility implied by the observed price of option i: A call pricing function can ...
Third, we will survey the purely nonparametric approaches such as kerned-based techniques or learning networks used to estimate an option pricing function and recover the other quantities of interest with ...
doi:10.2139/ssrn.463860
fatcat:jf7vikole5fzrnw5dey2q4q6se
Exploring OD patterns of interested region based on taxi trajectories
2016
Journal of Visualization
Traffics of different regions in a city have different Origin-Destination (OD) patterns, which potentially reveal the surrounding traffic context and social functions. ...
In this work, we present a visual analysis system to explore OD patterns of interested regions based on taxi trajectories. ...
Particularly, exclusive option provides the function of filtering out trajectories passing a certain area. ...
doi:10.1007/s12650-016-0357-7
fatcat:tgwmkorxlrgn3ma3l4dxpd6lwe
The Future of Work - Trends, Options, Problems
1992
European Journal of Public Health
Health in turn is a prominent social good that tends to be unequally distributed in the population in function of its accessibility and the conditions of its social production. ...
This sketch starts with a short recall of some aspects of our socio-economic system's meso-and macro-history, distinguishes three models of macro-economic organization that coexist unequally in present-day ...
The new systems are of an increasingly flexible application. Their handling demands cognitive functioning on higher levels of abstraction than is the case of more traditional work skills. ...
doi:10.1093/eurpub/2.2.96
fatcat:2tx3ttchbffcvlwl4rihhuvvxm
« Previous
Showing results 1 — 15 out of 136,983 results