-
Notifications
You must be signed in to change notification settings - Fork 0
/
recsys_rl.bib
295 lines (270 loc) · 9.91 KB
/
recsys_rl.bib
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
% Encoding: UTF-8
@inproceedings{bandits,
author = {Li, Lihong and Chu, Wei and Langford, John and Schapire, Robert E.},
title = {A Contextual-Bandit Approach to Personalized News Article Recommendation},
year = {2010},
isbn = {9781605587998},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/1772690.1772758},
doi = {10.1145/1772690.1772758},
booktitle = {Proceedings of the 19th International Conference on World Wide Web},
pages = {661–670},
numpages = {10},
keywords = {contextual bandit, recommender systems, exploration/exploitation dilemma, web service, personalization},
location = {Raleigh, North Carolina, USA},
series = {WWW ’10}
}
@inproceedings{page-wise,
doi = {10.1145/3240323.3240374},
url = {https://doi.org/10.1145/3240323.3240374},
year = {2018},
publisher = {{ACM} Press},
author = {Xiangyu Zhao and Long Xia and Liang Zhang and Zhuoye Ding and Dawei Yin and Jiliang Tang},
title = {Deep reinforcement learning for page-wise recommendations},
booktitle = {Proceedings of the 12th {ACM} Conference on Recommender Systems - {RecSys} {\textquotesingle}18}
}
@article{list-wise,
title={Deep Reinforcement Learning for List-wise Recommendations},
author={Xiangyu Zhao and Liang Zhang and Zhuoye Ding and Dawei Yin and Yihong Zhao and Jiliang Tang},
journal={ArXiv},
year={2018},
volume={abs/1801.00209}
}
@article{CF_MF,
author = {Koren, Yehuda and Bell, Robert and Volinsky, Chris},
title = {Matrix Factorization Techniques for Recommender Systems},
year = {2009},
issue_date = {August 2009},
publisher = {IEEE Computer Society Press},
address = {Washington, DC, USA},
volume = {42},
number = {8},
issn = {0018-9162},
url = {https://doi.org/10.1109/MC.2009.263},
doi = {10.1109/MC.2009.263},
journal = {Computer},
month = aug,
pages = {30–37},
numpages = {8},
keywords = {Computational intelligence, Matrix factorization, Netflix Prize}
}
@inproceedings{GoogleNewsCF,
author = {Das, Abhinandan S. and Datar, Mayur and Garg, Ashutosh and Rajaram, Shyam},
title = {Google News Personalization: Scalable Online Collaborative Filtering},
year = {2007},
isbn = {9781595936547},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/1242572.1242610},
doi = {10.1145/1242572.1242610},
booktitle = {Proceedings of the 16th International Conference on World Wide Web},
pages = {271–280},
numpages = {10},
keywords = {PLSI, mapreduce, minhash, personalization, Google news, oneline recommendation system, scalable collaborative filtering},
location = {Banff, Alberta, Canada},
series = {WWW ’07}
}
@article{content-based,
author = {Philip, Simon and Shola, Peter and Abari, Ovye},
year = {2014},
month = {10},
pages = {},
title = {Application of Content-Based Approach in Research Paper Recommendation System for a Digital Library},
volume = {5},
journal = {International Journal of Advanced Computer Science and Applications},
doi = {10.14569/IJACSA.2014.051006}
}
@InProceedings{content-based_news,
author="Kompan, Michal
and Bielikov{\'a}, M{\'a}ria",
editor="Buccafurri, Francesco
and Semeraro, Giovanni",
title="Content-Based News Recommendation",
booktitle="E-Commerce and Web Technologies",
year="2010",
publisher="Springer Berlin Heidelberg",
address="Berlin, Heidelberg",
pages="61--72",
isbn="978-3-642-15208-5"
}
@inproceedings{mdp,
author = {Shani, Guy and Brafman, Ronen I. and Heckerman, David},
title = {An MDP-Based Recommender System},
year = {2002},
isbn = {1558608974},
publisher = {Morgan Kaufmann Publishers Inc.},
address = {San Francisco, CA, USA},
booktitle = {Proceedings of the Eighteenth Conference on Uncertainty in Artificial Intelligence},
pages = {453–460},
numpages = {8},
location = {Alberta, Canada},
series = {UAI’02}
}
@misc{ppo,
title={Proximal Policy Optimization Algorithms},
author={John Schulman and Filip Wolski and Prafulla Dhariwal and Alec Radford and Oleg Klimov},
year={2017},
eprint={1707.06347},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
@misc{trulyPPO,
title={Truly Proximal Policy Optimization},
author={Yuhui Wang and Hao He and Chao Wen and Xiaoyang Tan},
year={2019},
eprint={1903.07940},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
@InProceedings{dpg,
title = {Deterministic Policy Gradient Algorithms},
author = {David Silver and Guy Lever and Nicolas Heess and Thomas Degris and Daan Wierstra and Martin Riedmiller},
booktitle = {Proceedings of the 31st International Conference on Machine Learning},
pages = {387--395},
year = {2014},
editor = {Eric P. Xing and Tony Jebara},
volume = {32},
number = {1},
series = {Proceedings of Machine Learning Research},
address = {Bejing, China},
month = {22--24 Jun},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v32/silver14.pdf},
url = {http://proceedings.mlr.press/v32/silver14.html},
}
@inproceedings{ddpg,
added-at = {2019-07-12T20:04:55.000+0200},
author = {Lillicrap, Timothy P. and Hunt, Jonathan J. and Pritzel, Alexander and Heess, Nicolas and Erez, Tom and Tassa, Yuval and Silver, David and Wierstra, Daan},
biburl = {https://www.bibsonomy.org/bibtex/22708c349821330660afb992aec2be5d1/lanteunis},
booktitle = {ICLR},
crossref = {conf/iclr/2016},
editor = {Bengio, Yoshua and LeCun, Yann},
ee = {http://arxiv.org/abs/1509.02971},
interhash = {b791167abe535c8525f6a9bf62fcc1ab},
intrahash = {2708c349821330660afb992aec2be5d1},
keywords = {},
timestamp = {2019-07-12T20:04:55.000+0200},
title = {Continuous control with deep reinforcement learning.},
year = 2016
}
@inproceedings{td3,
author = {Scott Fujimoto and
Herke van Hoof and
David Meger},
editor = {Jennifer G. Dy and
Andreas Krause},
title = {Addressing Function Approximation Error in Actor-Critic Methods},
booktitle = {Proceedings of the 35th International Conference on Machine Learning,
{ICML} 2018, Stockholmsm{\"{a}}ssan, Stockholm, Sweden, July
10-15, 2018},
series = {Proceedings of Machine Learning Research},
volume = {80},
pages = {1582--1591},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v80/fujimoto18a.html},
timestamp = {Wed, 03 Apr 2019 18:17:30 +0200},
biburl = {https://dblp.org/rec/conf/icml/FujimotoHM18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@Article{Uhlenbeck30,
author = "G. E. Uhlenbeck and L. S. Ornstein",
title = "On the theory of the Brownian motion",
journal = "Phys. Rev.",
volume = "36",
number = "3",
pages = "823--841",
year = "1930",
}
@article{Liu2018DeepRL,
title={Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling},
author={Feng Liu and Ruiming Tang and Xutao Li and Yunming Ye and Haokun Chen and Huifeng Guo and Yuzhou Zhang},
journal={ArXiv},
year={2018},
volume={abs/1810.12027}
}
@misc{vae,
title={Auto-Encoding Variational Bayes},
author={Diederik P Kingma and Max Welling},
year={2013},
eprint={1312.6114},
archivePrefix={arXiv},
primaryClass={stat.ML}
}
@inproceedings{pg,
author = {Sutton, Richard S. and McAllester, David and Singh, Satinder and Mansour, Yishay},
title = {Policy Gradient Methods for Reinforcement Learning with Function Approximation},
year = {1999},
publisher = {MIT Press},
address = {Cambridge, MA, USA},
booktitle = {Proceedings of the 12th International Conference on Neural Information Processing Systems},
pages = {1057–1063},
numpages = {7},
location = {Denver, CO},
series = {NIPS’99}
}
@book{sutton_book,
author = {Sutton, Richard S. and Barto, Andrew G.},
title = {Reinforcement Learning: An Introduction},
year = {2018},
isbn = {0262039249},
publisher = {A Bradford Book},
address = {Cambridge, MA, USA}
}
@article{ML_1M,
author = {Harper, F. Maxwell and Konstan, Joseph A.},
title = {The MovieLens Datasets: History and Context},
year = {2015},
issue_date = {January 2016},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
volume = {5},
number = {4},
issn = {2160-6455},
url = {https://doi.org/10.1145/2827872},
doi = {10.1145/2827872},
journal = {ACM Trans. Interact. Intell. Syst.},
month = dec,
articleno = {19},
numpages = {19},
keywords = {ratings, Datasets, MovieLens, recommendations}
}
@article{first,
title={DRN: A Deep Reinforcement Learning Framework for News Recommendation},
author={Guanjie Zheng and Fuzheng Zhang and Zihan Zheng and Yang Xiang and Nicholas Jing Yuan and Xing Xie and Zhenhui Li},
journal={Proceedings of the 2018 World Wide Web Conference},
year={2018}
}
@inproceedings{latest,
author = {Liu, Feng and Guo, Huifeng and Li, Xutao and Tang, Ruiming and Ye, Yunming and He, Xiuqiang},
title = {End-to-End Deep Reinforcement Learning Based Recommendation with Supervised Embedding},
year = {2020},
isbn = {9781450368223},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3336191.3371858},
doi = {10.1145/3336191.3371858},
booktitle = {Proceedings of the 13th International Conference on Web Search and Data Mining},
pages = {384–392},
numpages = {9},
keywords = {supervised embedding, recommendation, end-to-end, reinforcement learning},
location = {Houston, TX, USA},
series = {WSDM ’20}
}
@misc{wolpertinger,
title={Deep Reinforcement Learning in Large Discrete Action Spaces},
author={Gabriel Dulac-Arnold and Richard Evans and Hado van Hasselt and Peter Sunehag and Timothy Lillicrap and Jonathan Hunt and Timothy Mann and Theophane Weber and Thomas Degris and Ben Coppin},
year={2015},
eprint={1512.07679},
archivePrefix={arXiv},
primaryClass={cs.AI}
}
@misc{catalyst,
author = {Kolesnikov, Sergey},
title = {Accelerated DL R&D},
year = {2018},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/catalyst-team/catalyst}},
}