# encoding:utf-8
@article{peters2019ergodicity,
  title={The ergodicity problem in economics},
  author={Peters, Ole},
  journal={Nature Physics},
  volume={15},
  number={12},
  pages={1216--1221},
  year={2019},
  publisher={Nature Publishing Group}
}
@inproceedings{boyan1996learning,
  title={Learning evaluation functions for large acyclic domains},
  author={Boyan, Justin A and Moore, Andrew W},
  booktitle={Proceedings of the Thirteenth International Conference on  Machine Learning},
  pages={63--70},
  year={1996}
}
@article{boyan2002technical,
  title={Technical update: Least-squares temporal difference learning},
  author={Boyan, Justin A},
  journal={Machine learning},
  volume={49},
  number={2-3},
  pages={233--246},
  year={2002},
  publisher={Springer}
}
@article{pakes1969some,
  title={Some conditions for ergodicity and recurrence of Markov chains},
  author={Pakes, Anthony G},
  journal={Operations Research},
  volume={17},
  number={6},
  pages={1058--1061},
  year={1969},
  publisher={INFORMS}
}
@article{kaplan1979sufficient,
  title={A sufficient condition of nonergodicity of a {Markov} chain (Corresp.)},
  author={Kaplan, Michael},
  journal={IEEE Transactions on Information Theory},
  volume={25},
  number={4},
  pages={470--471},
  year={1979},
  publisher={IEEE}
}
@article{wiewiora2003potential,
  title={Potential-based shaping and Q-value initialization are equivalent},
  author={Wiewiora, Eric},
  journal={Journal of Artificial Intelligence Research},
  volume={19},
  pages={205--208},
  year={2003}
}
@inproceedings{devlin2012dynamic,
  title={Dynamic potential-based reward shaping},
  author={Devlin, Sam Michael and Kudenko, Daniel},
  booktitle={11th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2012)},
  pages={433--440},
  year={2012},
  organization={IFAAMAS}
}
@misc{abdelkader20152048,
  title={2048 is NP-Complete},
  author={Abdelkader, Ahmed and Acharya, Aditya and Dasler, Philip},
  year={2015},
}
@incollection{bangole2023game,
  title={Game Playing (2048) Using Deep Neural Networks},
  author={Bangole, Narendra Kumar Rao and Moulya, RB and Pranthi, R and Reddy, Sreelekha and Namratha, R},
  booktitle={The Software Principles of Design for Data Modeling},
  pages={133--144},
  year={2023},
  publisher={IGI Global}
}
@inproceedings{matsuzaki2020further,
  title={A further investigation of neural network players for game 2048},
  author={Matsuzaki, Kiminori},
  booktitle={Advances in Computer Games: 16th International Conference, ACG 2019, Macao, China, August 11--13, 2019, Revised Selected Papers 16},
  pages={53--65},
  year={2020},
  organization={Springer}
}
@inproceedings{majeed2018q,
  title={On Q-learning Convergence for Non-Markov Decision Processes.},
  author={Majeed, Sultan Javed and Hutter, Marcus and others},
  booktitle={IJCAI},
  volume={18},
  pages={2546--2552},
  year={2018}
}
@article{guei2021optimistic,
  title={Optimistic temporal difference learning for 2048},
  author={Guei, Hung and Chen, Lung-Pin and Wu, I-Chen},
  journal={IEEE Transactions on Games},
  volume={14},
  number={3},
  pages={478--487},
  year={2022},
  publisher={IEEE}
}
@inproceedings{rodgers2014an,
  title={An investigation into 2048 AI strategies},
  author={Rodgers, Philip  and  Levine, John},
  booktitle={2014 IEEE Conference on Computational Intelligence and Games},
  pages={1--2},
  year={2014},
  organization={IEEE}
}
@inproceedings{szubert2014temporal,
  title={Temporal difference learning of n-tuple networks for the game 2048},
  author={Szubert, Marcin and Ja{\'s}kowski, Wojciech},
  booktitle={2014 IEEE Conference on Computational Intelligence and Games},
  pages={1--8},
  year={2014},
  organization={IEEE}
}
@article{jaskowski2017mastering,
  title={Mastering 2048 with delayed temporal coherence learning, multistage weight promotion, redundant encoding, and carousel shaping},
  author={Ja{\'s}kowski, Wojciech},
  journal={IEEE Transactions on Games},
  volume={10},
  number={1},
  pages={3--14},
  year={2017},
  publisher={IEEE}
}
@article{yeh2016multistage,
  title={Multistage temporal difference learning for 2048-like games},
  author={Yeh, Kun-Hao and Wu, I-Chen and Hsueh, Chu-Hsuan and Chang, Chia-Chuan and Liang, Chao-Chin and Chiang, Han},
  journal={IEEE Transactions on Computational Intelligence and AI in Games},
  volume={9},
  number={4},
  pages={369--380},
  year={2016},
  publisher={IEEE}
}
@inproceedings{wu2014multi,
  title={Multi-stage temporal difference learning for 2048},
  author={Wu, I-Chen and Yeh, Kun-Hao and Liang, Chao-Chin and Chang, Chia-Chuan and Chiang, Han},
  booktitle={Technologies and Applications of Artificial Intelligence: 19th International Conference, TAAI 2014, Taipei, Taiwan, November 21-23, 2014. Proceedings},
  pages={366--378},
  year={2014},
  organization={Springer}
}
@article{kondo2019playing,
  title={Playing game 2048 with deep convolutional neural networks trained by supervised learning},
  author={Kondo, Naoki and Matsuzaki, Kiminori},
  journal={Journal of Information Processing},
  volume={27},
  pages={340--347},
  year={2019},
  publisher={Information Processing Society of Japan}
}
@inproceedings{matsuzaki2017developing,
  title={Developing a 2048 player with backward temporal coherence learning and restart},
  author={Matsuzaki, Kiminori},
  booktitle={Advances in Computer Games: 15th International Conferences, ACG 2017, Leiden, The Netherlands, July 3--5, 2017, Revised Selected Papers 15},
  pages={176--187},
  year={2017},
  organization={Springer}
}
@inproceedings{matsuzaki2016systematic,
  title={Systematic selection of N-tuple networks with consideration of interinfluence for game 2048},
  author={Matsuzaki, Kiminori},
  booktitle={2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)},
  pages={186--193},
  year={2016},
  organization={IEEE}
}
@inproceedings{oka2016systematic,
  title={Systematic selection of N-tuple networks for 2048},
  author={Oka, Kazuto and Matsuzaki, Kiminori},
  booktitle={International Conference on Computers and Games},
  pages={81--92},
  year={2016},
  organization={Springer}
}
@article{matsuzaki2021developing,
  title={Developing value networks for game 2048 with reinforcement learning},
  author={Matsuzaki, Kiminori},
  journal={Journal of Information Processing},
  volume={29},
  pages={336--346},
  year={2021},
  publisher={Information Processing Society of Japan}
}
@book{Sutton2018book,
  author = {Sutton, Richard S. and Barto, Andrew G.},
  edition = {Second},
  publisher = {The MIT Press},
  title = {Reinforcement Learning: An Introduction},
  year = {2018 }
}