Algorithm Research & References
End-to-End One-Shot Path-Planning Algorithm
Bian, T., Xing, Y., & Zolotas, A. (2022). End-to-End One-Shot Path-Planning Algorithm for an Autonomous Vehicle Based on a Convolutional Neural Network Considering Traversability Cost. Sensors, 22(24), 9682.
View PaperMastering 2048 with Delayed Temporal Coherence Learning
Jaśkowski, W. (2016). Mastering 2048 with Delayed Temporal Coherence Learning, Multi-Stage Weight Promotion, Redundant Encoding and Carousel Shaping. arXiv.
View PaperDynamic Simulation Monte-Carlo Tree Search
Lan, L.-C., Tsai, M.-Y., Wu, T.-R., Wu, I.-C., & Hsieh, C.-J. (2020). Learning to Stop: Dynamic Simulation Monte-Carlo Tree Search. arXiv.
View PaperBSNN: Bistable Neurons
Li, Y., Zeng, Y., & Zhao, D. (2021). BSNN: Towards Faster and Better Conversion of Artificial Neural Networks to Spiking Neural Networks with Bistable Neurons. arXiv.
View PaperMinimax and Expectimax Algorithm
Munir, R. (n.d.). Minimax and Expectimax Algorithm to Solve 2048. Informatika - Institut Teknologi Bandung.
View PDFInvestigation into 2048 AI Strategies
Rodgers, P., & Levine, J. (2014). An Investigation into 2048 AI Strategies. IEEE Conference on Computational Intelligence and Games.
DeepSearch via Monte Carlo Tree Search
Wu, F., Xuan, W., Qi, H., Lu, X., Tu, A., Li, L. E., & Choi, Y. (2025). DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search. arXiv.
View Paper