outputs/outputs_20230420_235048/main.bbl

\begin{thebibliography}{10}
\providecommand{\natexlab}[1]{#1}
\providecommand{\url}[1]{\texttt{#1}}
\expandafter\ifx\csname urlstyle\endcsname\relax
  \providecommand{\doi}[1]{doi: #1}\else
  \providecommand{\doi}{doi: \begingroup \urlstyle{rm}\Url}\fi

\bibitem[Akshita~Mittel(2018)]{1809.00397}
Himanshi~Yadav Akshita~Mittel, Sowmya~Munukutla.
\newblock Visual transfer between atari games using competitive reinforcement
  learning.
\newblock \emph{arXiv preprint arXiv:1809.00397}, 2018.
\newblock URL \url{http://arxiv.org/abs/1809.00397v1}.

\bibitem[Kai~Arulkumaran(2017)]{1708.05866}
Miles Brundage Anil Anthony~Bharath Kai~Arulkumaran, Marc Peter~Deisenroth.
\newblock A brief survey of deep reinforcement learning.
\newblock \emph{arXiv preprint arXiv:1708.05866}, 2017.
\newblock URL \url{http://arxiv.org/abs/1708.05866v2}.

\bibitem[Kenny~Young(2019)]{1903.03176}
Tian~Tian Kenny~Young.
\newblock Minatar: An atari-inspired testbed for thorough and reproducible
  reinforcement learning experiments.
\newblock \emph{arXiv preprint arXiv:1903.03176}, 2019.
\newblock URL \url{http://arxiv.org/abs/1903.03176v2}.

\bibitem[Li~Meng(2021)]{2106.14642}
Morten Goodwin Paal~Engelstad Li~Meng, Anis~Yazidi.
\newblock Expert q-learning: Deep reinforcement learning with coarse state
  values from offline expert examples.
\newblock \emph{arXiv preprint arXiv:2106.14642}, 2021.
\newblock URL \url{http://arxiv.org/abs/2106.14642v3}.

\bibitem[Mahipal~Jadeja(2017)]{1709.05067}
Agam~Shah Mahipal~Jadeja, Neelanshi~Varia.
\newblock Deep reinforcement learning for conversational ai.
\newblock \emph{arXiv preprint arXiv:1709.05067}, 2017.
\newblock URL \url{http://arxiv.org/abs/1709.05067v1}.

\bibitem[Ngan~Le(2021)]{2108.11510}
Kashu Yamazaki Khoa Luu Marios~Savvides Ngan~Le, Vidhiwar Singh~Rathour.
\newblock Deep reinforcement learning in computer vision: A comprehensive
  survey.
\newblock \emph{arXiv preprint arXiv:2108.11510}, 2021.
\newblock URL \url{http://arxiv.org/abs/2108.11510v1}.

\bibitem[Qiyue~Yin(2022)]{2212.00253}
Shengqi Shen Jun Yang Meijing Zhao Kaiqi Huang Bin Liang Liang~Wang Qiyue~Yin,
  Tongtong~Yu.
\newblock Distributed deep reinforcement learning: A survey and a multi-player
  multi-agent learning toolbox.
\newblock \emph{arXiv preprint arXiv:2212.00253}, 2022.
\newblock URL \url{http://arxiv.org/abs/2212.00253v1}.

\bibitem[Russell~Kaplan(2017)]{1704.05539}
Alexander~Sosa Russell~Kaplan, Christopher~Sauer.
\newblock Beating atari with natural language guided reinforcement learning.
\newblock \emph{arXiv preprint arXiv:1704.05539}, 2017.
\newblock URL \url{http://arxiv.org/abs/1704.05539v1}.

\bibitem[Sergey~Ivanov(2019)]{1906.10025}
Alexander~D'yakonov Sergey~Ivanov.
\newblock Modern deep reinforcement learning algorithms.
\newblock \emph{arXiv preprint arXiv:1906.10025}, 2019.
\newblock URL \url{http://arxiv.org/abs/1906.10025v2}.

\bibitem[Yang~Shao(2022)]{2203.16777}
Tadayuki Matsumura Taiki Fuji Kiyoto Ito Hiroyuki~Mizuno Yang~Shao, Quan~Kong.
\newblock Mask atari for deep reinforcement learning as pomdp benchmarks.
\newblock \emph{arXiv preprint arXiv:2203.16777}, 2022.
\newblock URL \url{http://arxiv.org/abs/2203.16777v1}.

\end{thebibliography}