Fetching the paper…
Reading the bibliography…
Information gathering in a partially observable environment can be formulated as a reinforcement learning (RL), problem where the reward depends on the agent's uncertainty.
Dropout: a simple way to prevent neural networks from overfitting
N Srivastava, G Hinton, A Krizhevsky, I Sutskever, and R Salakhutdinov. 2014 · 1958
Earlier work this paper cites.
Edge detection in pictures by computer using planning
M D Kelly. 1971 · 1971
Earlier work this paper cites.
Object recognition using vision and touch
P K Allen. 1985 · 1985
Earlier work this paper cites.
Active perception
R Bajcsy. 1988 · 1988
Earlier work this paper cites.
Active object recognition. In CVPR
D Wilkes and J K Tsotsos. 1992 · 1992
Earlier work this paper cites.
Simple statistical gradient-following algorithms for connectionist reinforcement learning
R J Williams. 1992 · 1992
Earlier work this paper cites.
Where to look next in 3d object search. In ISCV
Y Ye and J K Tsotsos. 1995 · 1995
Earlier work this paper cites.
Active mobile robot localization by entropy minimization. In EUROMICRO Workshop
W Burgard, D Fox, and S Thrun. 1997 · 1997
Earlier work this paper cites.
Planning and acting in partially observable stochastic domains
L P Kaelbling, M L. Littman, and A R Cassandra. 1998 · 1998
Earlier work this paper cites.
Gradient-based learning applied to document recognition
Y LeCun, L Bottou, Y Bengio, and P Haffner. 1998 · 1998
Earlier work this paper cites.
Convex optimization
S Boyd and L Vandenberghe. 2004 · 2004
Earlier work this paper cites.
Near-optimal nonmyopic value of information in graphical models. In UAI
A Krause and C Guestrin. 2005 · 2005
Earlier work this paper cites.
Sensor management using an active sensing approach
C Kreucher, K Kastella, and A O Hero. 2005 · 2005
Earlier work this paper cites.
Approximate dynamic programming for communication-constrained sensor network management
J L Williams, J W Fisher, and A S Willsky. 2007 · 2007
Earlier work this paper cites.
Active perception: Interactive manipulation for improving object detection
Q V Le, A Saxena, and A Y Ng. 2008 · 2008
Earlier work this paper cites.
Saliency, attention, and visual search: An information theoretic approach
N DB Bruce and J K Tsotsos. 2009 · 2009
Earlier work this paper cites.
A tutorial on particle filtering and smoothing: Fifteen years later
A Doucet and A M Johansen. 2009 · 2009
Earlier work this paper cites.
SarsaLandmark: an algorithm for learning in POMDPs with landmarks. In AAMAS
M R James and S Singh. 2009 · 2009
Earlier work this paper cites.
Sensor selection via convex optimization
S Joshi and S Boyd. 2009 · 2009
Cited alongside, same era.
A decision-theoretic approach to dynamic sensor selection in camera networks. In ICAPS
M T J Spaan and P U Lima. 2009 · 2009
Cited alongside, same era.
A POMDP extension with belief-dependent rewards. In NeurIPS
M Araya-lópez, V Thomas, O Buffet, and F Charpillet. 2010 · 2010
Cited alongside, same era.
Dynamic sensor selection for single target tracking in large video surveillance networks. In IEEE AVSS
E Monari and K Kroschel. 2010 · 2010
Cited alongside, same era.
Sensor management: Past, present, and future
A O Hero and D Cochran. 2011 · 2011
Cited alongside, same era.
What is a fenchel conjugate?
H Bauschke and Y Lucet. 2012 · 2012
Cited alongside, same era.
Improving information extraction by acquiring external evidence with reinforcement learning. In EMNLP
K Narasimhan, A Yala, and R Barzilay. 2016 · 2016
Later among the works it cites.
Control of memory, active perception, and action in minecraft. In ICML
J Oh, V Chockalingam, S Singh, and H Lee. 2016 · 2016
Later among the works it cites.
Theoretical perspectives on active sensing
S C H Yang, D M Wolpert, and M Lengyel. 2016 · 2016
Later among the works it cites.
Learning algorithms for active learning. In ICML
P Bachman, A Sordoni, and A Trischler. 2017 · 2017
Later among the works it cites.
Learning in POMDPs with Monte Carlo Tree Search. In ICML
S Katt, F A Oliehoek, and C Amato. 2017 · 2017
Later among the works it cites.
Curiosity-driven exploration by self-supervised prediction. In ICML
D Pathak, P Agrawal, A A Efros, and T Darrell. 2017 · 2017
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Improved information gain estimates for decision tree induction. In ICML
S Nowozin. 2012 · 2012
Cited alongside, same era.
Real-time tracking and fast retrieval of persons in multiple surveillance cameras of a shopping mall. In Multisensor, Multisource Information Fusion
H Bouma, J Baan, S Landsmeer, C Kruszynski, G van Antwerpen, and J Dijk. 2013 · 2013
Cited alongside, same era.
Generative adversarial nets. In NeurIPS
I Goodfellow, J Pouget-Abadie, M Mirza, B Xu, D Warde-Farley, S Ozair, A Courville, and Y Bengio. 2014 · 2014
Cited alongside, same era.
Adam: A method for stochastic optimization
D Kingma and J Ba. 2014 · 2014
Cited alongside, same era.
Recurrent models of visual attention. In NeurIPS
V Mnih, N Heess, A Graves, and K Kavukcuoglu. 2014 · 2014
Cited alongside, same era.
Camera selection for tracking in distributed smart camera networks
L Tessens, M Morbee, H Aghajan, and W Philips. 2014 · 2014
Cited alongside, same era.
Later among the works it cites.
Proximal policy optimization algorithms
J Schulman, F Wolski, P Dhariwal, A Radford, and O Klimov. 2017 · 2017
Later among the works it cites.
Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms
H Xiao, K Rasul, and R Vollgraf. 2017 · 2017
Later among the works it cites.
Revisiting active perception
R Bajcsy, Y Aloimonos, and J K Tsotsos. 2018 · 2018
Later among the works it cites.
Mine: mutual information neural estimation
M I Belghazi, A Baratin, S Rajeswar, S Ozair, Y Bengio, A Courville, and R D Hjelm. 2018 · 2018
Later among the works it cites.
Ask the right questions: Active question reformulation with reinforcement learning
C Buck, J Bulian, M Ciaramita, W Gajewski, A Gesmundo, N Houlsby, and W Wang. 2018 · 2018
Later among the works it cites.
Diversity is all you need: Learning skills without a reward function
B Eysenbach, A Gupta, J Ibarz, and S Levine. 2018 · 2018
Later among the works it cites.
Deep variational reinforcement learning for POMDPs. In ICML
M Igl, L Zintgraf, T A Le, F Wood, and S Whiteson. 2018 · 2018
Later among the works it cites.
Exploiting submodularity for scaling Up active perception
Y Satsangi, S Whiteson, F A. Oliehoek, and M Spaan. 2018 · 2018
Later among the works it cites.
Online active perception for partially observable Markov decision process with limited budget
M Ghasemi and U Topcu. 2019 · 2019
Later among the works it cites.
A layered architecture for active perception: Image classification using deep reinforcement learning
H K Mousavi, G Liu, W Yuan, M Takáč, H Muñoz-Avila, and N Motee. 2019 · 2019
Later among the works it cites.
Deep reinforcement learning with double q-learning. In Thirtieth AAAI conference on artificial intelligence
H Van Hasselt, A Guez, and D Silver. 2016 · 2094
Closest in time.