-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdeeprl-algorithms-breakout.aux
140 lines (140 loc) · 10.2 KB
/
deeprl-algorithms-breakout.aux
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
\relax
\providecommand\hyper@newdestlabel[2]{}
\providecommand\HyperFirstAtBeginDocument{\AtBeginDocument}
\HyperFirstAtBeginDocument{\ifx\hyper@anchor\@undefined
\global\let\oldcontentsline\contentsline
\gdef\contentsline#1#2#3#4{\oldcontentsline{#1}{#2}{#3}}
\global\let\oldnewlabel\newlabel
\gdef\newlabel#1#2{\newlabelxx{#1}#2}
\gdef\newlabelxx#1#2#3#4#5#6{\oldnewlabel{#1}{{#2}{#3}}}
\AtEndDocument{\ifx\hyper@anchor\@undefined
\let\contentsline\oldcontentsline
\let\newlabel\oldnewlabel
\fi}
\fi}
\global\let\hyper@last\relax
\gdef\HyperFirstAtBeginDocument#1{#1}
\providecommand\HyField@AuxAddToFields[1]{}
\providecommand\HyField@AuxAddToCoFields[2]{}
\citation{mnih2015humanlevel}
\citation{DBLP:journals/corr/MnihBMGLHSK16}
\citation{capstone-proposal}
\citation{openai-gym}
\citation{DBLP:journals/corr/abs-1207-4708}
\citation{baselines}
\citation{mnih2015humanlevel}
\citation{DBLP:journals/corr/WangFL15}
\citation{DBLP:journals/corr/MnihBMGLHSK16}
\citation{DBLP:conf/amcc/DegrisPS12}
\@writefile{lof}{\contentsline {figure}{\numberline {1}{\ignorespaces Atari 2600 Breakout game in Stella}}{3}{figure.1}}
\newlabel{fig:breakout-01}{{1}{3}{Atari 2600 Breakout game in Stella}{figure.1}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {2}{\ignorespaces Deep neural network from DQN}}{4}{figure.2}}
\newlabel{fig:experience-replay}{{2}{4}{Deep neural network from DQN}{figure.2}{}}
\citation{mnih2015humanlevel}
\citation{huber_loss}
\@writefile{lof}{\contentsline {figure}{\numberline {3}{\ignorespaces Example of a CNN with dimensions m X n}}{6}{figure.3}}
\newlabel{fig:cnn-example}{{3}{6}{Example of a CNN with dimensions m X n}{figure.3}{}}
\citation{DBLP:journals/corr/PlappertHDSCCAA17}
\citation{DBLP:journals/corr/HasseltGS15}
\citation{DBLP:journals/corr/HasseltGS15}
\@writefile{lof}{\contentsline {figure}{\numberline {4}{\ignorespaces Deep neural network from DQN}}{7}{figure.4}}
\newlabel{fig:dqn-architecture}{{4}{7}{Deep neural network from DQN}{figure.4}{}}
\citation{DBLP:journals/corr/SchaulQAS15}
\@writefile{lof}{\contentsline {figure}{\numberline {5}{\ignorespaces Deep neural network from Dueling-DQN}}{8}{figure.5}}
\newlabel{fig:dueling-dqn-architecture}{{5}{8}{Deep neural network from Dueling-DQN}{figure.5}{}}
\citation{DBLP:journals/corr/MnihBMGLHSK16}
\citation{DBLP:journals/corr/MnihBMGLHSK16}
\newlabel{alg:a2c-thread}{{1}{10}{A2C}{algorithm.1}{}}
\@writefile{loa}{\contentsline {algorithm}{\numberline {1}{\ignorespaces Synchronous Advantage Actor-Critic learner }}{10}{algorithm.1}}
\citation{rmsprop}
\citation{rmsprop-coursera}
\citation{intuitive_a2c}
\citation{mnih2015humanlevel}
\@writefile{lof}{\contentsline {figure}{\numberline {6}{\ignorespaces Author's top score}}{12}{figure.6}}
\newlabel{fig:top-score}{{6}{12}{Author's top score}{figure.6}{}}
\@writefile{lol}{\contentsline {lstlisting}{\numberline {1}bash version}{13}{lstlisting.1}}
\@writefile{lol}{\contentsline {lstlisting}{\numberline {2}bash version}{14}{lstlisting.2}}
\citation{mnih2015humanlevel}
\citation{mnih2015humanlevel}
\citation{LayerNorm}
\@writefile{lof}{\contentsline {figure}{\numberline {7}{\ignorespaces DQN Episodes}}{17}{figure.7}}
\newlabel{fig:dqn-episodes}{{7}{17}{DQN Episodes}{figure.7}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {8}{\ignorespaces DQN Mean 100 episodes rewards}}{18}{figure.8}}
\newlabel{fig:dqn-mean-100-episodes-rewards}{{8}{18}{DQN Mean 100 episodes rewards}{figure.8}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {9}{\ignorespaces DQN \% time spent exploring}}{18}{figure.9}}
\newlabel{fig:dqn-percent-time-spent-exploring}{{9}{18}{DQN \% time spent exploring}{figure.9}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {10}{\ignorespaces DQN Steps}}{18}{figure.10}}
\newlabel{fig:dqn-steps-clean}{{10}{18}{DQN Steps}{figure.10}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {11}{\ignorespaces DQN Mean of summed rewards}}{19}{figure.11}}
\newlabel{fig:dqn-mean-summed-rewards}{{11}{19}{DQN Mean of summed rewards}{figure.11}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {12}{\ignorespaces DQN Median of summed rewards}}{19}{figure.12}}
\newlabel{fig:dqn-median-summed-rewards}{{12}{19}{DQN Median of summed rewards}{figure.12}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {13}{\ignorespaces DQN Standard Deviance of summed rewards}}{20}{figure.13}}
\newlabel{fig:dqn-sd-summed-rewards}{{13}{20}{DQN Standard Deviance of summed rewards}{figure.13}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {14}{\ignorespaces DQN Mean of the number of games played}}{20}{figure.14}}
\newlabel{fig:dqn-mean-ngp}{{14}{20}{DQN Mean of the number of games played}{figure.14}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {15}{\ignorespaces DQN Median of the number of games played}}{21}{figure.15}}
\newlabel{fig:dqn-median-ngp}{{15}{21}{DQN Median of the number of games played}{figure.15}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {16}{\ignorespaces DQN Standard deviation of the number of games played}}{21}{figure.16}}
\newlabel{fig:dqn-sd-ngp}{{16}{21}{DQN Standard deviation of the number of games played}{figure.16}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {17}{\ignorespaces Non-dueling DQN Mean of summed rewards}}{22}{figure.17}}
\newlabel{fig:dqn-nd-mean-summed-rewards}{{17}{22}{Non-dueling DQN Mean of summed rewards}{figure.17}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {18}{\ignorespaces Non-dueling DQN Median of summed rewards}}{22}{figure.18}}
\newlabel{fig:dqn-nd-median-summed-rewards}{{18}{22}{Non-dueling DQN Median of summed rewards}{figure.18}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {19}{\ignorespaces Non-dueling DQN Standard Deviance of summed rewards}}{23}{figure.19}}
\newlabel{fig:dqn-nd-sd-summed-rewards}{{19}{23}{Non-dueling DQN Standard Deviance of summed rewards}{figure.19}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {20}{\ignorespaces Non-dueling DQN Mean of the number of games played}}{23}{figure.20}}
\newlabel{fig:dqn-nd-mean-ngp}{{20}{23}{Non-dueling DQN Mean of the number of games played}{figure.20}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {21}{\ignorespaces Non-dueling DQN Median of the number of games played}}{24}{figure.21}}
\newlabel{fig:dqn-nd-median-ngp}{{21}{24}{Non-dueling DQN Median of the number of games played}{figure.21}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {22}{\ignorespaces Non-dueling DQN Standard deviation of the number of games played}}{24}{figure.22}}
\newlabel{fig:dqn-nd-sd-ngp}{{22}{24}{Non-dueling DQN Standard deviation of the number of games played}{figure.22}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {23}{\ignorespaces A2C Explained Variance}}{25}{figure.23}}
\newlabel{fig:a2c-explained_variance}{{23}{25}{A2C Explained Variance}{figure.23}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {24}{\ignorespaces A2C FPS}}{25}{figure.24}}
\newlabel{fig:a2c-fps}{{24}{25}{A2C FPS}{figure.24}{}}
\citation{DBLP:journals/corr/MnihBMGLHSK16}
\@writefile{lof}{\contentsline {figure}{\numberline {25}{\ignorespaces A2C Number of updates}}{26}{figure.25}}
\newlabel{fig:a2c-nupdates}{{25}{26}{A2C Number of updates}{figure.25}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {26}{\ignorespaces A2C Policy entropy}}{26}{figure.26}}
\newlabel{fig:a2c-policy-entropy}{{26}{26}{A2C Policy entropy}{figure.26}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {27}{\ignorespaces A2C Total timesteps}}{27}{figure.27}}
\newlabel{fig:a2c-total-timesteps}{{27}{27}{A2C Total timesteps}{figure.27}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {28}{\ignorespaces A2C Value Loss}}{27}{figure.28}}
\newlabel{fig:a2c-value-loss-clean}{{28}{27}{A2C Value Loss}{figure.28}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {29}{\ignorespaces A2C Mean of summed rewards}}{28}{figure.29}}
\newlabel{fig:a2c-mean-summed-rewards}{{29}{28}{A2C Mean of summed rewards}{figure.29}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {30}{\ignorespaces A2C Median of summed rewards}}{28}{figure.30}}
\newlabel{fig:a2c-median-summed-rewards}{{30}{28}{A2C Median of summed rewards}{figure.30}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {31}{\ignorespaces A2C Standard Deviance of summed rewards}}{29}{figure.31}}
\newlabel{fig:a2c-sd-summed-rewards}{{31}{29}{A2C Standard Deviance of summed rewards}{figure.31}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {32}{\ignorespaces A2C Mean of the number of games played}}{29}{figure.32}}
\newlabel{fig:a2c-mean-ngp}{{32}{29}{A2C Mean of the number of games played}{figure.32}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {33}{\ignorespaces A2C Median of the number of games played}}{30}{figure.33}}
\newlabel{fig:a2c-median-ngp}{{33}{30}{A2C Median of the number of games played}{figure.33}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {34}{\ignorespaces A2C Standard deviation of the number of games played}}{30}{figure.34}}
\newlabel{fig:a2c-sd-ngp}{{34}{30}{A2C Standard deviation of the number of games played}{figure.34}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {35}{\ignorespaces A2C LNLSTM Mean of summed rewards}}{32}{figure.35}}
\newlabel{fig:a2c-lnlstm-mean-summed-rewards}{{35}{32}{A2C LNLSTM Mean of summed rewards}{figure.35}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {36}{\ignorespaces A2C mean of summed rewards vs humans}}{33}{figure.36}}
\newlabel{fig:a2c-vs-humans-mean}{{36}{33}{A2C mean of summed rewards vs humans}{figure.36}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {37}{\ignorespaces A2C median of summed rewards vs humans}}{33}{figure.37}}
\newlabel{fig:a2c-vs-humans-median}{{37}{33}{A2C median of summed rewards vs humans}{figure.37}{}}
\bibstyle{plain}
\bibdata{bibliography}
\bibcite{LayerNorm}{1}
\bibcite{DBLP:journals/corr/abs-1207-4708}{2}
\bibcite{capstone-proposal}{3}
\bibcite{rmsprop-coursera}{4}
\bibcite{DBLP:conf/amcc/DegrisPS12}{5}
\bibcite{baselines}{6}
\bibcite{intuitive_a2c}{7}
\bibcite{DBLP:journals/corr/MnihBMGLHSK16}{8}
\bibcite{mnih2015humanlevel}{9}
\bibcite{openai-gym}{10}
\bibcite{DBLP:journals/corr/PlappertHDSCCAA17}{11}
\bibcite{DBLP:journals/corr/SchaulQAS15}{12}
\bibcite{DBLP:journals/corr/HasseltGS15}{13}
\bibcite{DBLP:journals/corr/WangFL15}{14}
\bibcite{huber_loss}{15}
\bibcite{rmsprop}{16}