AAAI Best Papers CollectingThe Association for the Advancement of Artificial Intelligence. Formerly known as the American Association for Artificial Intelligence, it is a non-profit academic research organization dedicated to promoting scientific research into the nature of intelligent behavior.
national conference on artificial intelligence, (2020)
The Winograd Schema Challenge (WSC), proposed by Levesque et al. (2011) as an alternative to the Turing Test, was originally designed as a pronoun resolution problem that cannot be solved based on statistical patterns in large text corpora. However, recent studies suggest that ...
Cited by34BibtexViews83Links
0
0
Kévin Fauvel, Daniel Balouek-Thomert, Diego Melgar, Pedro Silva,Anthony Simonet,Gabriel Antoniu,Alexandru Costan, Véronique Masson,Manish Parashar,Ivan Rodero, Alexandre Termier
national conference on artificial intelligence, (2020)
Our research aims to improve the accuracy of Earthquake Early Warning (EEW) systems by means of machine learning. EEW systems are designed to detect and characterize medium and large earthquakes before their damaging effects reach a certain location. Traditional EEW methods based...
Cited by3BibtexViews50Links
0
0
Vidal Alcazar, Patricia Riddle,Michael Barley
national conference on artificial intelligence, (2020)
Cited by1BibtexViews25Links
0
0
Xiaohui Bei, Zihao Li, Jinyan Liu,Shengxin Liu, Xinhang Lu
national conference on artificial intelligence, (2020)
We show that an envy-freeness for mixed goods allocation always exists for any number of agents
Cited by0BibtexViews29Links
0
0
national conference on artificial intelligence, (2019)
We introduced variants of counterfactual regret minimization that discount prior iterations, leading to stronger performance than the prior stateof-the-art CFR+, in settings that involve large mistakes
Cited by28BibtexViews47Links
0
0
national conference on artificial intelligence, (2019)
In contrast to existing works, this paper presents the first general framework and algorithm for intelligent agents to learn to teach in a multiagent environment
Cited by26BibtexViews86Links
0
0
national conference on artificial intelligence, (2019)
We introduce the zero shot feedback challenge
Cited by7BibtexViews34Links
0
0
Yonathan Efroni, Gal Dalal,Bruno Scherrer,Shie Mannor
national conference on artificial intelligence, (2019)
We show that even when partial policy evaluation is performed and noise is added to it, along with a noisy policy improvement stage, the above Policy Iteration scheme converges with a γh contraction coefficient
Cited by5BibtexViews77Links
0
0
Yash Chandak,Georgios Theocharous, Chris Nota,Philip S. Thomas
CoRR, (2019)
In this work we established first steps towards developing the lifelong Markov decision processes setup for dealing with action sets that change over time
Cited by0BibtexViews26Links
0
0
AAAI, (2018)
We first study how the parameters M and τ can affect the performance of Memory-Augmented Monte Carlo Tree Search, since these two parameters together control the degree of generalization
Cited by12BibtexViews130Links
0
0
Russell Stewart,Stefano Ermon
national conference on artificial intelligence, (2017)
We have introduced a new method for using physics and other domain constraints to supervise neural networks
Cited by146BibtexViews55Links
0
0
AAAI, pp.3411-3417, (2016)
In this paper we introduced MM, the first bidirectional heuristic search algorithm guaranteed to meet in the middle
Cited by44BibtexViews67Links
0
0
AAAI, pp.3335-3341, (2015)
We introduced potential heuristics as a fast alternative to optimal cost partitioning
Cited by64BibtexViews60Links
0
0
AAAI, pp.2410-2416, (2014)
Since selection bias is a common problem across many disciplines, the methods developed in this paper should help to understand, formalize, and alleviate this problem in a broad range of data-intensive applications
Cited by71BibtexViews52Links
0
0
AAAI, (2013)
We introduced the HC-Search framework for structured prediction whose principal feature is the separation of the cost function from search heuristic
Cited by20BibtexViews44Links
0
0
AAAI, (2013)
We show that Shuffled Multiple-Instance Learning can significantly improve the performance of an MI classifier, and is well-suited for domains such as active learning in which few initial labeled bags are available to a classifier
Cited by6BibtexViews45Links
0
0
AAAI, (2012)
We propose a novel summarization framework called Document Summarization based on Data Reconstruction which selects the most representative sentences that can best reconstruct the entire document
Cited by98BibtexViews174Links
0
0
AAAI, pp.942-948, (2012)
We presented a novel joint optimization model over SVM classifications and principal component analysis to conduct SVM training with indefinite kernels assisted by kernel component analysis
Cited by28BibtexViews103Links
0
0
AAAI, (2011)
To evaluate whether such computational complexity is important in practice, we have proposed two new approximation methods that try to minimize the number of manipulators
Cited by81BibtexViews43Links
0
0
AAAI, (2011)
We proved the surprising result that this simple opportunistic policy is competitive with a clairvoyant solution that is informed in advance of the budget in each timestep and when each patch will be available
Cited by37BibtexViews77Links
0
0