-
Notifications
You must be signed in to change notification settings - Fork 0
/
bibliography.bib
255 lines (236 loc) · 9.26 KB
/
bibliography.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
@article{mnih2015humanlevel,
added-at = {2017-11-15T22:03:15.000+0100},
author = {Mnih, Volodymyr and Kavukcuoglu, Koray and Silver, David and Rusu, Andrei A. and Veness, Joel and Bellemare, Marc G. and Graves, Alex and Riedmiller, Martin and Fidjeland, Andreas K. and Ostrovski, Georg and Petersen, Stig and Beattie, Charles and Sadik, Amir and Antonoglou, Ioannis and King, Helen and Kumaran, Dharshan and Wierstra, Daan and Legg, Shane and Hassabis, Demis},
biburl = {https://www.bibsonomy.org/bibtex/2fb15f4471c81dc2b9edf2304cb2f7083/lukasw},
description = {Human-level control through deep reinforcement learning - nature14236.pdf},
interhash = {eac59980357d99db87b341b61ef6645f},
intrahash = {fb15f4471c81dc2b9edf2304cb2f7083},
issn = {00280836},
journal = {Nature},
keywords = {atari final},
month = feb,
number = 7540,
pages = {529--533},
publisher = {Nature Publishing Group, a division of Macmillan Publishers Limited. All Rights Reserved.},
timestamp = {2017-11-15T22:03:15.000+0100},
title = {Human-level control through deep reinforcement learning},
url = {http://dx.doi.org/10.1038/nature14236},
volume = 518,
year = 2015
}
@article{DBLP:journals/corr/MnihBMGLHSK16,
author = {Volodymyr Mnih and
Adri{\`{a}} Puigdom{\`{e}}nech Badia and
Mehdi Mirza and
Alex Graves and
Timothy P. Lillicrap and
Tim Harley and
David Silver and
Koray Kavukcuoglu},
title = {Asynchronous Methods for Deep Reinforcement Learning},
journal = {CoRR},
volume = {abs/1602.01783},
year = {2016},
url = {http://arxiv.org/abs/1602.01783},
archivePrefix = {arXiv},
eprint = {1602.01783},
timestamp = {Wed, 07 Jun 2017 14:43:09 +0200},
biburl = {http://dblp.org/rec/bib/journals/corr/MnihBMGLHSK16},
bibsource = {dblp computer science bibliography, http://dblp.org}
}
@article{DBLP:journals/corr/WangBHMMKF16,
author = {Ziyu Wang and
Victor Bapst and
Nicolas Heess and
Volodymyr Mnih and
R{\'{e}}mi Munos and
Koray Kavukcuoglu and
Nando de Freitas},
title = {Sample Efficient Actor-Critic with Experience Replay},
journal = {CoRR},
volume = {abs/1611.01224},
year = {2016},
url = {http://arxiv.org/abs/1611.01224},
archivePrefix = {arXiv},
eprint = {1611.01224},
timestamp = {Tue, 08 Aug 2017 15:06:57 +0200},
biburl = {http://dblp.org/rec/bib/journals/corr/WangBHMMKF16},
bibsource = {dblp computer science bibliography, http://dblp.org}
}
@article{DBLP:journals/corr/WangFL15,
author = {Ziyu Wang and
Nando de Freitas and
Marc Lanctot},
title = {Dueling Network Architectures for Deep Reinforcement Learning},
journal = {CoRR},
volume = {abs/1511.06581},
year = {2015},
url = {http://arxiv.org/abs/1511.06581},
archivePrefix = {arXiv},
eprint = {1511.06581},
timestamp = {Tue, 08 Aug 2017 15:06:57 +0200},
biburl = {http://dblp.org/rec/bib/journals/corr/WangFL15},
bibsource = {dblp computer science bibliography, http://dblp.org}
}
@inproceedings{DBLP:conf/amcc/DegrisPS12,
author = {Thomas Degris and
Patrick M. Pilarski and
Richard S. Sutton},
title = {Model-Free reinforcement learning with continuous action in practice},
booktitle = {American Control Conference, {ACC} 2012, Montreal, QC, Canada, June
27-29, 2012},
pages = {2177--2182},
year = {2012},
crossref = {DBLP:conf/amcc/2012},
url = {http://ieeexplore.ieee.org/document/6315022/},
timestamp = {Sun, 30 Apr 2017 09:41:50 +0200},
biburl = {http://dblp.org/rec/bib/conf/amcc/DegrisPS12},
bibsource = {dblp computer science bibliography, http://dblp.org}
}
@proceedings{DBLP:conf/amcc/2012,
title = {American Control Conference, {ACC} 2012, Montreal, QC, Canada, June
27-29, 2012},
publisher = {{IEEE}},
year = {2012},
url = {http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6297579},
isbn = {978-1-4577-1095-7},
timestamp = {Fri, 20 Feb 2015 09:36:34 +0100},
biburl = {http://dblp.org/rec/bib/conf/amcc/2012},
bibsource = {dblp computer science bibliography, http://dblp.org}
}
@article{DBLP:journals/corr/PlappertHDSCCAA17,
author = {Matthias Plappert and
Rein Houthooft and
Prafulla Dhariwal and
Szymon Sidor and
Richard Y. Chen and
Xi Chen and
Tamim Asfour and
Pieter Abbeel and
Marcin Andrychowicz},
title = {Parameter Space Noise for Exploration},
journal = {CoRR},
volume = {abs/1706.01905},
year = {2017},
url = {http://arxiv.org/abs/1706.01905},
archivePrefix = {arXiv},
eprint = {1706.01905},
timestamp = {Mon, 03 Jul 2017 13:29:02 +0200},
biburl = {http://dblp.org/rec/bib/journals/corr/PlappertHDSCCAA17},
bibsource = {dblp computer science bibliography, http://dblp.org}
}
@article{DBLP:journals/corr/HasseltGS15,
author = {Hado van Hasselt and
Arthur Guez and
David Silver},
title = {Deep Reinforcement Learning with Double Q-learning},
journal = {CoRR},
volume = {abs/1509.06461},
year = {2015},
url = {http://arxiv.org/abs/1509.06461},
archivePrefix = {arXiv},
eprint = {1509.06461},
timestamp = {Wed, 07 Jun 2017 14:40:43 +0200},
biburl = {http://dblp.org/rec/bib/journals/corr/HasseltGS15},
bibsource = {dblp computer science bibliography, http://dblp.org}
}
@article{DBLP:journals/corr/SchaulQAS15,
author = {Tom Schaul and
John Quan and
Ioannis Antonoglou and
David Silver},
title = {Prioritized Experience Replay},
journal = {CoRR},
volume = {abs/1511.05952},
year = {2015},
url = {http://arxiv.org/abs/1511.05952},
archivePrefix = {arXiv},
eprint = {1511.05952},
timestamp = {Wed, 07 Jun 2017 14:42:32 +0200},
biburl = {http://dblp.org/rec/bib/journals/corr/SchaulQAS15},
bibsource = {dblp computer science bibliography, http://dblp.org}
}
@article{DBLP:journals/corr/abs-1207-4708,
author = {Marc G. Bellemare and
Yavar Naddaf and
Joel Veness and
Michael Bowling},
title = {The Arcade Learning Environment: An Evaluation Platform for General
Agents},
journal = {CoRR},
volume = {abs/1207.4708},
year = {2012},
url = {http://arxiv.org/abs/1207.4708},
archivePrefix = {arXiv},
eprint = {1207.4708},
timestamp = {Wed, 07 Jun 2017 14:43:03 +0200},
biburl = {https://dblp.org/rec/bib/journals/corr/abs-1207-4708},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{LayerNorm,
author = {Jimmy Lei Ba and
Jamie Ryan Kiros and
Geoffrey Hinton},
title = {Layer Normalization},
year = {2016},
url = {https://arxiv.org/abs/1607.06450},
archivePrefix = {arXiv},
eprint = {1607.06450}
}
@misc{capstone-proposal,
author = {Andr\'e Carvalho},
title = {Proposal - Learning to play video games with Machine Learning},
year = {2017},
note = {Last access in 14 January 2018},
howpublished= {\url{https://github.com/andretadeu/capstone-proposal/blob/master/capstone_proposal.md}}
}
@misc{baselines,
author = {Dhariwal, Prafulla and Hesse, Christopher and Klimov, Oleg and Nichol, Alex and Plappert, Matthias and Radford, Alec and Schulman, John and Sidor, Szymon and Wu, Yuhuai},
title = {OpenAI Baselines},
year = {2017},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/openai/baselines}},
}
@misc{huber_loss,
author = {Wikipedia},
title = {Huber Loss},
year = {2018},
note = {Last access in 14 January 2018},
howpublished= {\url{https://en.wikipedia.org/wiki/Huber_loss}}
}
@misc{rmsprop,
author = {Wikipedia},
title = {Stochastic Gradient Descent},
year = {2018},
note = {Last access in 10 March 2018},
howpublished= {\url{https://en.wikipedia.org/wiki/Stochastic_gradient_descent#RMSProp}}
}
@misc{rmsprop-coursera,
author = {Coursera and Geoffrey Hinton and Nitish
Srivastava and Kevin Swersky},
title = {Neural Networks for Machine Learning | Coursera},
year = {2018},
note = {Last access in 10 March 2018},
howpublished= {\url{https://www.coursera.org/learn/neural-networks}}
}
@misc{intuitive_a2c,
author = {Rudy Gilman},
title = {Intuitive RL: Intro to Advantage-Actor-Critic (A2C)},
year = {2018},
note = {Last access in 31 March 2018},
howpublished = {\url{https://hackernoon.com/intuitive-rl-intro-to-advantage-actor-critic-a2c-4ff545978752}}
}
@misc{cnn,
author = {Andrey Karpathy, Justin Johnson, et al},
title = {CS231n Convolutional Neural Networks for Visual Recognition},
year = {2018},
note = {Last access in 31 March 2018},
howpublished = {\url{http://cs231n.github.io/convolutional-networks/}}
}
@misc{openai-gym,
author = {OpenAI},
title = {Gym},
year = {2018},
howpublished = {\url{https://github.com/openai/gym}}
}