-
Notifications
You must be signed in to change notification settings - Fork 0
/
database_test.bib
277 lines (253 loc) · 10.2 KB
/
database_test.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
@#!##@%@{
}
@article{bartlett2021deep,
title={No authors doesn't produce any errors???},
author={ },
journal={Advances in Neural Information Processing Systems},
volume={30},
pages={87--201},
year={\n},
publisher={Cambridge University Press}
}
@article{bartlett2021deep,
title={lplpl},
author={\'Emeline Pierre and Spence von der Ohe},
journal={Advances in Neural Information Processing Systems},
volume={30},
pages={87--201},
year={2021},
publisher={Cambridge University Press}
}
@article{bartlett2021deep,
title={Deep learning: a statistical viewpoint},
author={Bartlett, Peter L and Montanari, Andrea and Rakhlin, Alexander},
journal={Acta numerica},
volume={30},
pages={87--201},
year={2021},
publisher={Cambridge University Press}
}
@inproceedings{mahmood2013representation,
title={Representation search through generate and test},
author={Mahmood, Ashique Rupam and Sutton, Richard S},
booktitle={Workshops at the Twenty-Seventh AAAI conference on artificial intelligence},
year={2013}
}
@pl{
}
@misc{faker,
author={Spence van der Ohe},
year={1934},
title={} what if the title is empty???
}
@article{tsybakov2004,
title={Optimal aggregation of classifiers in statistical learning},
author={Alexander B. Tsybakov},
journal={The Annals of Statistics},
year={2004},
}
@inproceedings{DBLP:conf/nips/RoyT95,
author = {Benjamin Van Roy and
John N. Tsitsiklis},
editor = {David S. Touretzky and
Michael Mozer and
Michael E. Hasselmo},
title = {Stable LInear Approximations to Dynamic Programming for Stochastic
Control Problems with Local Transitions},
booktitle = {Advances in Neural Information Processing Systems 8, NIPS, Denver,
CO, USA, November 27-30, 1995},
pages = {1045--1051},
publisher = {{MIT} Press},
year = {1995},
url = {http://papers.nips.cc/paper/1038-stable-linear-approximations-to-dynamic-programming-for-stochastic-control-problems-with-local-transitions},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/RoyT95.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@book{DBLP:books/lib/SuttonB98,
author = {Richard S. Sutton and
Andrew G. Barto},
title = {Reinforcement learning - an introduction},
series = {Adaptive computation and machine learning},
publisher = {MIT Press},
year = {1998},
url = {https://www.worldcat.org/oclc/37293240},
isbn = {978-0-262-19398-6},
timestamp = {Fri, 17 Jul 2020 16:12:40 +0200},
biburl = {https://dblp.org/rec/books/lib/SuttonB98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Abbasi-YadkoriPS11,
author = {Yasin Abbasi{-}Yadkori and
D{\'{a}}vid P{\'{a}}l and
Csaba Szepesv{\'{a}}ri},
editor = {John Shawe{-}Taylor and
Richard S. Zemel and
Peter L. Bartlett and
Fernando C. N. Pereira and
Kilian Q. Weinberger},
title = {Improved Algorithms for Linear Stochastic Bandits},
booktitle = {Advances in Neural Information Processing Systems 24: 25th Annual
Conference on Neural Information Processing Systems 2011. Proceedings
of a meeting held 12-14 December 2011, Granada, Spain},
pages = {2312--2320},
year = {2011},
url = {https://proceedings.neurips.cc/paper/2011/hash/e1d5be1c7f2f456670de3d53c7b54f4a-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/Abbasi-YadkoriPS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/OsbandDHASSMLSS20,
author = {Ian Osband and
Yotam Doron and
Matteo Hessel and
John Aslanides and
Eren Sezener and
Andre Saraiva and
Katrina McKinney and
Tor Lattimore and
Csaba Szepesv{\'{a}}ri and
Satinder Singh and
Benjamin Van Roy and
Richard S. Sutton and
David Silver and
Hado van Hasselt},
title = {Behaviour Suite for Reinforcement Learning},
booktitle = {8th International Conference on Learning Representations, {ICLR} 2020,
Addis Ababa, Ethiopia, April 26-30, 2020},
publisher = {OpenReview.net},
year = {2020},
url = {https://openreview.net/forum?id=rygf-kSYwH},
timestamp = {Mon, 15 May 2023 16:24:40 +0200},
biburl = {https://dblp.org/rec/conf/iclr/OsbandDHASSMLSS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{sutton2009fast,
title={Fast gradient-descent methods for temporal-difference learning with linear function approximation},
author={Sutton, Richard S and Maei, Hamid Reza and Precup, Doina and Bhatnagar, Shalabh and Silver, David and Szepesv{\'a}ri, Csaba and Wiewiora, Eric},
booktitle={Proceedings of the 26th annual international conference on machine learning},
pages={993--1000},
year={2009}
}
@article{abel2024definition,
title={A definition of continual reinforcement learning},
author={Abel, David and Barreto, Andr{\'e} and Van Roy, Benjamin and Precup, Doina and van Hasselt, Hado P and Singh, Satinder},
journal={Advances in Neural Information Processing Systems},
volume={36},
year={2024}
}
@inproceedings{DBLP:conf/nips/Abel0RPHS23,
author = {David Abel and
Andr{\'{e}} Barreto and
Benjamin Van Roy and
Doina Precup and
Hado Philip van Hasselt and
Satinder Singh},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {A Definition of Continual Reinforcement Learning},
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference
on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
LA, USA, December 10 - 16, 2023},
year = {2023},
url = {http://papers.nips.cc/paper\_files/paper/2023/hash/9d8cf1247786d6dfeefeeb53b8b5f6d7-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 16:26:20 +0100},
biburl = {https://dblp.org/rec/conf/nips/Abel0RPHS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@book{durrett2019,
title={Probability: theory and examples},
author={Rick Durrett},
year={2019},
publisher={Cambridge University Press}
}
@article{DBLP:journals/corr/SchulmanWDRK17,
author = {John Schulman and
Filip Wolski and
Prafulla Dhariwal and
Alec Radford and
Oleg Klimov},
title = {Proximal Policy Optimization Algorithms},
journal = {CoRR},
volume = {abs/1707.06347},
year = {2017},
url = {http://arxiv.org/abs/1707.06347},
eprinttype = {arXiv},
eprint = {1707.06347},
timestamp = {Mon, 13 Aug 2018 16:47:34 +0200},
biburl = {https://dblp.org/rec/journals/corr/SchulmanWDRK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@misc{schulman2017proximal,
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{xiao2024verbalized,
title={Verbalized Machine Learning: Revisiting Machine Learning with Language Models},
author={Tim Z. Xiao and Robert Bamler and Bernhard Schölkopf and Weiyang Liu},
year={2024},
eprint={2406.04344},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
@inproceedings{DBLP:conf/nips/KlochkovZ21,
author = {Yegor Klochkov and
Nikita Zhivotovskiy},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {Stability and Deviation Optimal Risk Bounds with Convergence Rate
{\textdollar}O(1/n){\textdollar}},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {5065--5076},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/286674e3082feb7e5afb92777e48821f-Abstract.html},
timestamp = {Tue, 03 May 2022 16:20:47 +0200},
biburl = {https://dblp.org/rec/conf/nips/KlochkovZ21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{klochkov2021stability,
title={Stability and Deviation Optimal Risk Bounds with Convergence Rate $ O (1/n) $},
author={Klochkov, Yegor and Zhivotovskiy, Nikita},
journal={Advances in Neural Information Processing Systems},
volume={34},
pages={5065--5076},
year={2021}
}
@inproceedings{klochkov2021,
author = {Yegor Klochkov and
Nikita Zhivotovskiy},
title = {Stability and Deviation Optimal Risk Bounds with Convergence Rate {\textdollar}O(1/n){\textdollar}},
booktitle = {Advances in Neural Information Processing Systems},
year = {2021},
}
@book{durrett2019,
title={Probability: theory and examples},
author={Rick Durrett},
year={2019},
publisher={Cambridge University Press}
}
@article{tsybakov2004,
title={Optimal aggregation of classifiers in statistical learning},
author={Alexander B. Tsybakov},
journal={The Annals of Statistics},
year={2004},
}
@book{zhang2023,
title={Mathematical analysis of machine learning algorithms},
author={Tong Zhang},
year={2023},
publisher={Cambridge University Press}
}