outputs/outputs_20230420_235048/ref.bib

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2212.00253,
          title = {Distributed Deep Reinforcement Learning: A Survey and A Multi-Player
  Multi-Agent Learning Toolbox},
          author = {Qiyue Yin , Tongtong Yu , Shengqi Shen , Jun Yang , Meijing Zhao , Kaiqi Huang , Bin Liang , Liang Wang}, 
          journal={arXiv preprint arXiv:2212.00253}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.00253v1}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2212.00253,
          title = {Distributed Deep Reinforcement Learning: A Survey and A Multi-Player
  Multi-Agent Learning Toolbox},
          author = {Qiyue Yin , Tongtong Yu , Shengqi Shen , Jun Yang , Meijing Zhao , Kaiqi Huang , Bin Liang , Liang Wang}, 
          journal={arXiv preprint arXiv:2212.00253}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.00253v1}
        }

@article{1709.05067,
          title = {Deep Reinforcement Learning for Conversational AI},
          author = {Mahipal Jadeja , Neelanshi Varia , Agam Shah}, 
          journal={arXiv preprint arXiv:1709.05067}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1709.05067v1}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2212.00253,
          title = {Distributed Deep Reinforcement Learning: A Survey and A Multi-Player
  Multi-Agent Learning Toolbox},
          author = {Qiyue Yin , Tongtong Yu , Shengqi Shen , Jun Yang , Meijing Zhao , Kaiqi Huang , Bin Liang , Liang Wang}, 
          journal={arXiv preprint arXiv:2212.00253}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.00253v1}
        }

@article{1709.05067,
          title = {Deep Reinforcement Learning for Conversational AI},
          author = {Mahipal Jadeja , Neelanshi Varia , Agam Shah}, 
          journal={arXiv preprint arXiv:1709.05067}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1709.05067v1}
        }

@article{1708.05866,
          title = {A Brief Survey of Deep Reinforcement Learning},
          author = {Kai Arulkumaran , Marc Peter Deisenroth , Miles Brundage , Anil Anthony Bharath}, 
          journal={arXiv preprint arXiv:1708.05866}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1708.05866v2}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2212.00253,
          title = {Distributed Deep Reinforcement Learning: A Survey and A Multi-Player
  Multi-Agent Learning Toolbox},
          author = {Qiyue Yin , Tongtong Yu , Shengqi Shen , Jun Yang , Meijing Zhao , Kaiqi Huang , Bin Liang , Liang Wang}, 
          journal={arXiv preprint arXiv:2212.00253}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.00253v1}
        }

@article{1709.05067,
          title = {Deep Reinforcement Learning for Conversational AI},
          author = {Mahipal Jadeja , Neelanshi Varia , Agam Shah}, 
          journal={arXiv preprint arXiv:1709.05067}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1709.05067v1}
        }

@article{1708.05866,
          title = {A Brief Survey of Deep Reinforcement Learning},
          author = {Kai Arulkumaran , Marc Peter Deisenroth , Miles Brundage , Anil Anthony Bharath}, 
          journal={arXiv preprint arXiv:1708.05866}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1708.05866v2}
        }

@article{1906.10025,
          title = {Modern Deep Reinforcement Learning Algorithms},
          author = {Sergey Ivanov , Alexander D'yakonov}, 
          journal={arXiv preprint arXiv:1906.10025}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1906.10025v2}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2212.00253,
          title = {Distributed Deep Reinforcement Learning: A Survey and A Multi-Player
  Multi-Agent Learning Toolbox},
          author = {Qiyue Yin , Tongtong Yu , Shengqi Shen , Jun Yang , Meijing Zhao , Kaiqi Huang , Bin Liang , Liang Wang}, 
          journal={arXiv preprint arXiv:2212.00253}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.00253v1}
        }

@article{1709.05067,
          title = {Deep Reinforcement Learning for Conversational AI},
          author = {Mahipal Jadeja , Neelanshi Varia , Agam Shah}, 
          journal={arXiv preprint arXiv:1709.05067}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1709.05067v1}
        }

@article{1708.05866,
          title = {A Brief Survey of Deep Reinforcement Learning},
          author = {Kai Arulkumaran , Marc Peter Deisenroth , Miles Brundage , Anil Anthony Bharath}, 
          journal={arXiv preprint arXiv:1708.05866}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1708.05866v2}
        }

@article{1906.10025,
          title = {Modern Deep Reinforcement Learning Algorithms},
          author = {Sergey Ivanov , Alexander D'yakonov}, 
          journal={arXiv preprint arXiv:1906.10025}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1906.10025v2}
        }

@article{2203.16777,
          title = {Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks},
          author = {Yang Shao , Quan Kong , Tadayuki Matsumura , Taiki Fuji , Kiyoto Ito , Hiroyuki Mizuno}, 
          journal={arXiv preprint arXiv:2203.16777}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2203.16777v1}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2212.00253,
          title = {Distributed Deep Reinforcement Learning: A Survey and A Multi-Player
  Multi-Agent Learning Toolbox},
          author = {Qiyue Yin , Tongtong Yu , Shengqi Shen , Jun Yang , Meijing Zhao , Kaiqi Huang , Bin Liang , Liang Wang}, 
          journal={arXiv preprint arXiv:2212.00253}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.00253v1}
        }

@article{1709.05067,
          title = {Deep Reinforcement Learning for Conversational AI},
          author = {Mahipal Jadeja , Neelanshi Varia , Agam Shah}, 
          journal={arXiv preprint arXiv:1709.05067}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1709.05067v1}
        }

@article{1708.05866,
          title = {A Brief Survey of Deep Reinforcement Learning},
          author = {Kai Arulkumaran , Marc Peter Deisenroth , Miles Brundage , Anil Anthony Bharath}, 
          journal={arXiv preprint arXiv:1708.05866}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1708.05866v2}
        }

@article{1906.10025,
          title = {Modern Deep Reinforcement Learning Algorithms},
          author = {Sergey Ivanov , Alexander D'yakonov}, 
          journal={arXiv preprint arXiv:1906.10025}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1906.10025v2}
        }

@article{2203.16777,
          title = {Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks},
          author = {Yang Shao , Quan Kong , Tadayuki Matsumura , Taiki Fuji , Kiyoto Ito , Hiroyuki Mizuno}, 
          journal={arXiv preprint arXiv:2203.16777}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2203.16777v1}
        }

@article{1704.05539,
          title = {Beating Atari with Natural Language Guided Reinforcement Learning},
          author = {Russell Kaplan , Christopher Sauer , Alexander Sosa}, 
          journal={arXiv preprint arXiv:1704.05539}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1704.05539v1}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2212.00253,
          title = {Distributed Deep Reinforcement Learning: A Survey and A Multi-Player
  Multi-Agent Learning Toolbox},
          author = {Qiyue Yin , Tongtong Yu , Shengqi Shen , Jun Yang , Meijing Zhao , Kaiqi Huang , Bin Liang , Liang Wang}, 
          journal={arXiv preprint arXiv:2212.00253}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.00253v1}
        }

@article{1709.05067,
          title = {Deep Reinforcement Learning for Conversational AI},
          author = {Mahipal Jadeja , Neelanshi Varia , Agam Shah}, 
          journal={arXiv preprint arXiv:1709.05067}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1709.05067v1}
        }

@article{1708.05866,
          title = {A Brief Survey of Deep Reinforcement Learning},
          author = {Kai Arulkumaran , Marc Peter Deisenroth , Miles Brundage , Anil Anthony Bharath}, 
          journal={arXiv preprint arXiv:1708.05866}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1708.05866v2}
        }

@article{1906.10025,
          title = {Modern Deep Reinforcement Learning Algorithms},
          author = {Sergey Ivanov , Alexander D'yakonov}, 
          journal={arXiv preprint arXiv:1906.10025}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1906.10025v2}
        }

@article{2203.16777,
          title = {Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks},
          author = {Yang Shao , Quan Kong , Tadayuki Matsumura , Taiki Fuji , Kiyoto Ito , Hiroyuki Mizuno}, 
          journal={arXiv preprint arXiv:2203.16777}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2203.16777v1}
        }

@article{1704.05539,
          title = {Beating Atari with Natural Language Guided Reinforcement Learning},
          author = {Russell Kaplan , Christopher Sauer , Alexander Sosa}, 
          journal={arXiv preprint arXiv:1704.05539}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1704.05539v1}
        }

@article{1809.00397,
          title = {Visual Transfer between Atari Games using Competitive Reinforcement
  Learning},
          author = {Akshita Mittel , Sowmya Munukutla , Himanshi Yadav}, 
          journal={arXiv preprint arXiv:1809.00397}, 
          year = {2018}, 
          url = {http://arxiv.org/abs/1809.00397v1}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2212.00253,
          title = {Distributed Deep Reinforcement Learning: A Survey and A Multi-Player
  Multi-Agent Learning Toolbox},
          author = {Qiyue Yin , Tongtong Yu , Shengqi Shen , Jun Yang , Meijing Zhao , Kaiqi Huang , Bin Liang , Liang Wang}, 
          journal={arXiv preprint arXiv:2212.00253}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.00253v1}
        }

@article{1709.05067,
          title = {Deep Reinforcement Learning for Conversational AI},
          author = {Mahipal Jadeja , Neelanshi Varia , Agam Shah}, 
          journal={arXiv preprint arXiv:1709.05067}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1709.05067v1}
        }

@article{1708.05866,
          title = {A Brief Survey of Deep Reinforcement Learning},
          author = {Kai Arulkumaran , Marc Peter Deisenroth , Miles Brundage , Anil Anthony Bharath}, 
          journal={arXiv preprint arXiv:1708.05866}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1708.05866v2}
        }

@article{1906.10025,
          title = {Modern Deep Reinforcement Learning Algorithms},
          author = {Sergey Ivanov , Alexander D'yakonov}, 
          journal={arXiv preprint arXiv:1906.10025}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1906.10025v2}
        }

@article{2203.16777,
          title = {Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks},
          author = {Yang Shao , Quan Kong , Tadayuki Matsumura , Taiki Fuji , Kiyoto Ito , Hiroyuki Mizuno}, 
          journal={arXiv preprint arXiv:2203.16777}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2203.16777v1}
        }

@article{1704.05539,
          title = {Beating Atari with Natural Language Guided Reinforcement Learning},
          author = {Russell Kaplan , Christopher Sauer , Alexander Sosa}, 
          journal={arXiv preprint arXiv:1704.05539}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1704.05539v1}
        }

@article{1809.00397,
          title = {Visual Transfer between Atari Games using Competitive Reinforcement
  Learning},
          author = {Akshita Mittel , Sowmya Munukutla , Himanshi Yadav}, 
          journal={arXiv preprint arXiv:1809.00397}, 
          year = {2018}, 
          url = {http://arxiv.org/abs/1809.00397v1}
        }

@article{1903.03176,
          title = {MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible
  Reinforcement Learning Experiments},
          author = {Kenny Young , Tian Tian}, 
          journal={arXiv preprint arXiv:1903.03176}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1903.03176v2}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2212.00253,
          title = {Distributed Deep Reinforcement Learning: A Survey and A Multi-Player
  Multi-Agent Learning Toolbox},
          author = {Qiyue Yin , Tongtong Yu , Shengqi Shen , Jun Yang , Meijing Zhao , Kaiqi Huang , Bin Liang , Liang Wang}, 
          journal={arXiv preprint arXiv:2212.00253}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.00253v1}
        }

@article{1709.05067,
          title = {Deep Reinforcement Learning for Conversational AI},
          author = {Mahipal Jadeja , Neelanshi Varia , Agam Shah}, 
          journal={arXiv preprint arXiv:1709.05067}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1709.05067v1}
        }

@article{1708.05866,
          title = {A Brief Survey of Deep Reinforcement Learning},
          author = {Kai Arulkumaran , Marc Peter Deisenroth , Miles Brundage , Anil Anthony Bharath}, 
          journal={arXiv preprint arXiv:1708.05866}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1708.05866v2}
        }

@article{1906.10025,
          title = {Modern Deep Reinforcement Learning Algorithms},
          author = {Sergey Ivanov , Alexander D'yakonov}, 
          journal={arXiv preprint arXiv:1906.10025}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1906.10025v2}
        }

@article{2203.16777,
          title = {Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks},
          author = {Yang Shao , Quan Kong , Tadayuki Matsumura , Taiki Fuji , Kiyoto Ito , Hiroyuki Mizuno}, 
          journal={arXiv preprint arXiv:2203.16777}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2203.16777v1}
        }

@article{1704.05539,
          title = {Beating Atari with Natural Language Guided Reinforcement Learning},
          author = {Russell Kaplan , Christopher Sauer , Alexander Sosa}, 
          journal={arXiv preprint arXiv:1704.05539}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1704.05539v1}
        }

@article{1809.00397,
          title = {Visual Transfer between Atari Games using Competitive Reinforcement
  Learning},
          author = {Akshita Mittel , Sowmya Munukutla , Himanshi Yadav}, 
          journal={arXiv preprint arXiv:1809.00397}, 
          year = {2018}, 
          url = {http://arxiv.org/abs/1809.00397v1}
        }

@article{1903.03176,
          title = {MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible
  Reinforcement Learning Experiments},
          author = {Kenny Young , Tian Tian}, 
          journal={arXiv preprint arXiv:1903.03176}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1903.03176v2}
        }

@article{1909.02765,
          title = {ILP-M Conv: Optimize Convolution Algorithm for Single-Image Convolution
  Neural Network Inference on Mobile GPUs},
          author = {Zhuoran Ji}, 
          journal={arXiv preprint arXiv:1909.02765}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1909.02765v2}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2212.00253,
          title = {Distributed Deep Reinforcement Learning: A Survey and A Multi-Player
  Multi-Agent Learning Toolbox},
          author = {Qiyue Yin , Tongtong Yu , Shengqi Shen , Jun Yang , Meijing Zhao , Kaiqi Huang , Bin Liang , Liang Wang}, 
          journal={arXiv preprint arXiv:2212.00253}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.00253v1}
        }

@article{1709.05067,
          title = {Deep Reinforcement Learning for Conversational AI},
          author = {Mahipal Jadeja , Neelanshi Varia , Agam Shah}, 
          journal={arXiv preprint arXiv:1709.05067}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1709.05067v1}
        }

@article{1708.05866,
          title = {A Brief Survey of Deep Reinforcement Learning},
          author = {Kai Arulkumaran , Marc Peter Deisenroth , Miles Brundage , Anil Anthony Bharath}, 
          journal={arXiv preprint arXiv:1708.05866}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1708.05866v2}
        }

@article{1906.10025,
          title = {Modern Deep Reinforcement Learning Algorithms},
          author = {Sergey Ivanov , Alexander D'yakonov}, 
          journal={arXiv preprint arXiv:1906.10025}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1906.10025v2}
        }

@article{2203.16777,
          title = {Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks},
          author = {Yang Shao , Quan Kong , Tadayuki Matsumura , Taiki Fuji , Kiyoto Ito , Hiroyuki Mizuno}, 
          journal={arXiv preprint arXiv:2203.16777}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2203.16777v1}
        }

@article{1704.05539,
          title = {Beating Atari with Natural Language Guided Reinforcement Learning},
          author = {Russell Kaplan , Christopher Sauer , Alexander Sosa}, 
          journal={arXiv preprint arXiv:1704.05539}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1704.05539v1}
        }

@article{1809.00397,
          title = {Visual Transfer between Atari Games using Competitive Reinforcement
  Learning},
          author = {Akshita Mittel , Sowmya Munukutla , Himanshi Yadav}, 
          journal={arXiv preprint arXiv:1809.00397}, 
          year = {2018}, 
          url = {http://arxiv.org/abs/1809.00397v1}
        }

@article{1903.03176,
          title = {MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible
  Reinforcement Learning Experiments},
          author = {Kenny Young , Tian Tian}, 
          journal={arXiv preprint arXiv:1903.03176}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1903.03176v2}
        }

@article{1909.02765,
          title = {ILP-M Conv: Optimize Convolution Algorithm for Single-Image Convolution
  Neural Network Inference on Mobile GPUs},
          author = {Zhuoran Ji}, 
          journal={arXiv preprint arXiv:1909.02765}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1909.02765v2}
        }

@article{1903.08131,
          title = {Kernel-based Translations of Convolutional Networks},
          author = {Corinne Jones , Vincent Roulet , Zaid Harchaoui}, 
          journal={arXiv preprint arXiv:1903.08131}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1903.08131v1}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2212.00253,
          title = {Distributed Deep Reinforcement Learning: A Survey and A Multi-Player
  Multi-Agent Learning Toolbox},
          author = {Qiyue Yin , Tongtong Yu , Shengqi Shen , Jun Yang , Meijing Zhao , Kaiqi Huang , Bin Liang , Liang Wang}, 
          journal={arXiv preprint arXiv:2212.00253}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.00253v1}
        }

@article{1709.05067,
          title = {Deep Reinforcement Learning for Conversational AI},
          author = {Mahipal Jadeja , Neelanshi Varia , Agam Shah}, 
          journal={arXiv preprint arXiv:1709.05067}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1709.05067v1}
        }

@article{1708.05866,
          title = {A Brief Survey of Deep Reinforcement Learning},
          author = {Kai Arulkumaran , Marc Peter Deisenroth , Miles Brundage , Anil Anthony Bharath}, 
          journal={arXiv preprint arXiv:1708.05866}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1708.05866v2}
        }

@article{1906.10025,
          title = {Modern Deep Reinforcement Learning Algorithms},
          author = {Sergey Ivanov , Alexander D'yakonov}, 
          journal={arXiv preprint arXiv:1906.10025}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1906.10025v2}
        }

@article{2203.16777,
          title = {Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks},
          author = {Yang Shao , Quan Kong , Tadayuki Matsumura , Taiki Fuji , Kiyoto Ito , Hiroyuki Mizuno}, 
          journal={arXiv preprint arXiv:2203.16777}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2203.16777v1}
        }

@article{1704.05539,
          title = {Beating Atari with Natural Language Guided Reinforcement Learning},
          author = {Russell Kaplan , Christopher Sauer , Alexander Sosa}, 
          journal={arXiv preprint arXiv:1704.05539}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1704.05539v1}
        }

@article{1809.00397,
          title = {Visual Transfer between Atari Games using Competitive Reinforcement
  Learning},
          author = {Akshita Mittel , Sowmya Munukutla , Himanshi Yadav}, 
          journal={arXiv preprint arXiv:1809.00397}, 
          year = {2018}, 
          url = {http://arxiv.org/abs/1809.00397v1}
        }

@article{1903.03176,
          title = {MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible
  Reinforcement Learning Experiments},
          author = {Kenny Young , Tian Tian}, 
          journal={arXiv preprint arXiv:1903.03176}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1903.03176v2}
        }

@article{1909.02765,
          title = {ILP-M Conv: Optimize Convolution Algorithm for Single-Image Convolution
  Neural Network Inference on Mobile GPUs},
          author = {Zhuoran Ji}, 
          journal={arXiv preprint arXiv:1909.02765}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1909.02765v2}
        }

@article{1903.08131,
          title = {Kernel-based Translations of Convolutional Networks},
          author = {Corinne Jones , Vincent Roulet , Zaid Harchaoui}, 
          journal={arXiv preprint arXiv:1903.08131}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1903.08131v1}
        }

@article{2212.09507,
          title = {VC dimensions of group convolutional neural networks},
          author = {Philipp Christian Petersen , Anna Sepliarskaia}, 
          journal={arXiv preprint arXiv:2212.09507}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.09507v1}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2212.00253,
          title = {Distributed Deep Reinforcement Learning: A Survey and A Multi-Player
  Multi-Agent Learning Toolbox},
          author = {Qiyue Yin , Tongtong Yu , Shengqi Shen , Jun Yang , Meijing Zhao , Kaiqi Huang , Bin Liang , Liang Wang}, 
          journal={arXiv preprint arXiv:2212.00253}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.00253v1}
        }

@article{1709.05067,
          title = {Deep Reinforcement Learning for Conversational AI},
          author = {Mahipal Jadeja , Neelanshi Varia , Agam Shah}, 
          journal={arXiv preprint arXiv:1709.05067}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1709.05067v1}
        }

@article{1708.05866,
          title = {A Brief Survey of Deep Reinforcement Learning},
          author = {Kai Arulkumaran , Marc Peter Deisenroth , Miles Brundage , Anil Anthony Bharath}, 
          journal={arXiv preprint arXiv:1708.05866}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1708.05866v2}
        }

@article{1906.10025,
          title = {Modern Deep Reinforcement Learning Algorithms},
          author = {Sergey Ivanov , Alexander D'yakonov}, 
          journal={arXiv preprint arXiv:1906.10025}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1906.10025v2}
        }

@article{2203.16777,
          title = {Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks},
          author = {Yang Shao , Quan Kong , Tadayuki Matsumura , Taiki Fuji , Kiyoto Ito , Hiroyuki Mizuno}, 
          journal={arXiv preprint arXiv:2203.16777}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2203.16777v1}
        }

@article{1704.05539,
          title = {Beating Atari with Natural Language Guided Reinforcement Learning},
          author = {Russell Kaplan , Christopher Sauer , Alexander Sosa}, 
          journal={arXiv preprint arXiv:1704.05539}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1704.05539v1}
        }

@article{1809.00397,
          title = {Visual Transfer between Atari Games using Competitive Reinforcement
  Learning},
          author = {Akshita Mittel , Sowmya Munukutla , Himanshi Yadav}, 
          journal={arXiv preprint arXiv:1809.00397}, 
          year = {2018}, 
          url = {http://arxiv.org/abs/1809.00397v1}
        }

@article{1903.03176,
          title = {MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible
  Reinforcement Learning Experiments},
          author = {Kenny Young , Tian Tian}, 
          journal={arXiv preprint arXiv:1903.03176}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1903.03176v2}
        }

@article{1909.02765,
          title = {ILP-M Conv: Optimize Convolution Algorithm for Single-Image Convolution
  Neural Network Inference on Mobile GPUs},
          author = {Zhuoran Ji}, 
          journal={arXiv preprint arXiv:1909.02765}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1909.02765v2}
        }

@article{1903.08131,
          title = {Kernel-based Translations of Convolutional Networks},
          author = {Corinne Jones , Vincent Roulet , Zaid Harchaoui}, 
          journal={arXiv preprint arXiv:1903.08131}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1903.08131v1}
        }

@article{2212.09507,
          title = {VC dimensions of group convolutional neural networks},
          author = {Philipp Christian Petersen , Anna Sepliarskaia}, 
          journal={arXiv preprint arXiv:2212.09507}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.09507v1}
        }

@article{2303.08631,
          title = {Smoothed Q-learning},
          author = {David Barber}, 
          journal={arXiv preprint arXiv:2303.08631}, 
          year = {2023}, 
          url = {http://arxiv.org/abs/2303.08631v1}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2212.00253,
          title = {Distributed Deep Reinforcement Learning: A Survey and A Multi-Player
  Multi-Agent Learning Toolbox},
          author = {Qiyue Yin , Tongtong Yu , Shengqi Shen , Jun Yang , Meijing Zhao , Kaiqi Huang , Bin Liang , Liang Wang}, 
          journal={arXiv preprint arXiv:2212.00253}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.00253v1}
        }

@article{1709.05067,
          title = {Deep Reinforcement Learning for Conversational AI},
          author = {Mahipal Jadeja , Neelanshi Varia , Agam Shah}, 
          journal={arXiv preprint arXiv:1709.05067}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1709.05067v1}
        }

@article{1708.05866,
          title = {A Brief Survey of Deep Reinforcement Learning},
          author = {Kai Arulkumaran , Marc Peter Deisenroth , Miles Brundage , Anil Anthony Bharath}, 
          journal={arXiv preprint arXiv:1708.05866}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1708.05866v2}
        }

@article{1906.10025,
          title = {Modern Deep Reinforcement Learning Algorithms},
          author = {Sergey Ivanov , Alexander D'yakonov}, 
          journal={arXiv preprint arXiv:1906.10025}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1906.10025v2}
        }

@article{2203.16777,
          title = {Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks},
          author = {Yang Shao , Quan Kong , Tadayuki Matsumura , Taiki Fuji , Kiyoto Ito , Hiroyuki Mizuno}, 
          journal={arXiv preprint arXiv:2203.16777}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2203.16777v1}
        }

@article{1704.05539,
          title = {Beating Atari with Natural Language Guided Reinforcement Learning},
          author = {Russell Kaplan , Christopher Sauer , Alexander Sosa}, 
          journal={arXiv preprint arXiv:1704.05539}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1704.05539v1}
        }

@article{1809.00397,
          title = {Visual Transfer between Atari Games using Competitive Reinforcement
  Learning},
          author = {Akshita Mittel , Sowmya Munukutla , Himanshi Yadav}, 
          journal={arXiv preprint arXiv:1809.00397}, 
          year = {2018}, 
          url = {http://arxiv.org/abs/1809.00397v1}
        }

@article{1903.03176,
          title = {MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible
  Reinforcement Learning Experiments},
          author = {Kenny Young , Tian Tian}, 
          journal={arXiv preprint arXiv:1903.03176}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1903.03176v2}
        }

@article{1909.02765,
          title = {ILP-M Conv: Optimize Convolution Algorithm for Single-Image Convolution
  Neural Network Inference on Mobile GPUs},
          author = {Zhuoran Ji}, 
          journal={arXiv preprint arXiv:1909.02765}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1909.02765v2}
        }

@article{1903.08131,
          title = {Kernel-based Translations of Convolutional Networks},
          author = {Corinne Jones , Vincent Roulet , Zaid Harchaoui}, 
          journal={arXiv preprint arXiv:1903.08131}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1903.08131v1}
        }

@article{2212.09507,
          title = {VC dimensions of group convolutional neural networks},
          author = {Philipp Christian Petersen , Anna Sepliarskaia}, 
          journal={arXiv preprint arXiv:2212.09507}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.09507v1}
        }

@article{2303.08631,
          title = {Smoothed Q-learning},
          author = {David Barber}, 
          journal={arXiv preprint arXiv:2303.08631}, 
          year = {2023}, 
          url = {http://arxiv.org/abs/2303.08631v1}
        }

@article{2106.14642,
          title = {Expert Q-learning: Deep Reinforcement Learning with Coarse State Values
  from Offline Expert Examples},
          author = {Li Meng , Anis Yazidi , Morten Goodwin , Paal Engelstad}, 
          journal={arXiv preprint arXiv:2106.14642}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.14642v3}
        }

@article{2108.11510,
          title = {Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey},
          author = {Ngan Le , Vidhiwar Singh Rathour , Kashu Yamazaki , Khoa Luu , Marios Savvides}, 
          journal={arXiv preprint arXiv:2108.11510}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2108.11510v1}
        }

@article{2212.00253,
          title = {Distributed Deep Reinforcement Learning: A Survey and A Multi-Player
  Multi-Agent Learning Toolbox},
          author = {Qiyue Yin , Tongtong Yu , Shengqi Shen , Jun Yang , Meijing Zhao , Kaiqi Huang , Bin Liang , Liang Wang}, 
          journal={arXiv preprint arXiv:2212.00253}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.00253v1}
        }

@article{1709.05067,
          title = {Deep Reinforcement Learning for Conversational AI},
          author = {Mahipal Jadeja , Neelanshi Varia , Agam Shah}, 
          journal={arXiv preprint arXiv:1709.05067}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1709.05067v1}
        }

@article{1708.05866,
          title = {A Brief Survey of Deep Reinforcement Learning},
          author = {Kai Arulkumaran , Marc Peter Deisenroth , Miles Brundage , Anil Anthony Bharath}, 
          journal={arXiv preprint arXiv:1708.05866}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1708.05866v2}
        }

@article{1906.10025,
          title = {Modern Deep Reinforcement Learning Algorithms},
          author = {Sergey Ivanov , Alexander D'yakonov}, 
          journal={arXiv preprint arXiv:1906.10025}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1906.10025v2}
        }

@article{2203.16777,
          title = {Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks},
          author = {Yang Shao , Quan Kong , Tadayuki Matsumura , Taiki Fuji , Kiyoto Ito , Hiroyuki Mizuno}, 
          journal={arXiv preprint arXiv:2203.16777}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2203.16777v1}
        }

@article{1704.05539,
          title = {Beating Atari with Natural Language Guided Reinforcement Learning},
          author = {Russell Kaplan , Christopher Sauer , Alexander Sosa}, 
          journal={arXiv preprint arXiv:1704.05539}, 
          year = {2017}, 
          url = {http://arxiv.org/abs/1704.05539v1}
        }

@article{1809.00397,
          title = {Visual Transfer between Atari Games using Competitive Reinforcement
  Learning},
          author = {Akshita Mittel , Sowmya Munukutla , Himanshi Yadav}, 
          journal={arXiv preprint arXiv:1809.00397}, 
          year = {2018}, 
          url = {http://arxiv.org/abs/1809.00397v1}
        }

@article{1903.03176,
          title = {MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible
  Reinforcement Learning Experiments},
          author = {Kenny Young , Tian Tian}, 
          journal={arXiv preprint arXiv:1903.03176}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1903.03176v2}
        }

@article{1909.02765,
          title = {ILP-M Conv: Optimize Convolution Algorithm for Single-Image Convolution
  Neural Network Inference on Mobile GPUs},
          author = {Zhuoran Ji}, 
          journal={arXiv preprint arXiv:1909.02765}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1909.02765v2}
        }

@article{1903.08131,
          title = {Kernel-based Translations of Convolutional Networks},
          author = {Corinne Jones , Vincent Roulet , Zaid Harchaoui}, 
          journal={arXiv preprint arXiv:1903.08131}, 
          year = {2019}, 
          url = {http://arxiv.org/abs/1903.08131v1}
        }

@article{2212.09507,
          title = {VC dimensions of group convolutional neural networks},
          author = {Philipp Christian Petersen , Anna Sepliarskaia}, 
          journal={arXiv preprint arXiv:2212.09507}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2212.09507v1}
        }

@article{2303.08631,
          title = {Smoothed Q-learning},
          author = {David Barber}, 
          journal={arXiv preprint arXiv:2303.08631}, 
          year = {2023}, 
          url = {http://arxiv.org/abs/2303.08631v1}
        }

@article{2106.14642,
          title = {Expert Q-learning: Deep Reinforcement Learning with Coarse State Values
  from Offline Expert Examples},
          author = {Li Meng , Anis Yazidi , Morten Goodwin , Paal Engelstad}, 
          journal={arXiv preprint arXiv:2106.14642}, 
          year = {2021}, 
          url = {http://arxiv.org/abs/2106.14642v3}
        }

@article{2211.05075,
          title = {Supporting AI/ML Security Workers through an Adversarial Techniques,
  Tools, and Common Knowledge (AI/ML ATT&CK) Framework},
          author = {Mohamad Fazelnia , Ahmet Okutan , Mehdi Mirakhorli}, 
          journal={arXiv preprint arXiv:2211.05075}, 
          year = {2022}, 
          url = {http://arxiv.org/abs/2211.05075v1}
        }