Playing the Game of 2048

Benchmarks archive 2025-07-28

1 leaderboard table shown for this task, 1 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

1 dataset whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

26 shown of 26 papers with code (57 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation
  27 Aug 2021 10 repositories listed Syntology ran 13 of 16 samples · 3 unverified · 5 pointer-only (licence)
  Since the introduction of the transformer model by Vaswani et al.
• GSPMD: General and Scalable Parallelization for ML Computation Graphs
  10 May 2021 4 repositories listed Syntology ran 0 of 4 samples · 4 unverified
  We present GSPMD, an automatic, compiler-based parallelization system for common machine learning computations.
• Mastering 2048 with Delayed Temporal Coherence Learning, Multi-Stage Weight Promotion, Redundant Encoding and Carousel Shaping
  18 Apr 2016 4 repositories listed
  With the aim to develop a strong 2048 playing program, we employ temporal difference learning with systematic n-tuple networks.
• Planning in Stochastic Environments with a Learned Model
  29 Sep 2021 2 repositories listed
  However, previous instantiations of this approach were limited to the use of deterministic models.
• Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization
  13 Sep 2021 2 repositories listed
  To this end, we propose a novel spatial-separated curve rendering network(S²CRNet) for efficient and high-resolution image harmonization for the first time.
• Long Short-Term Transformer for Online Action Detection
  7 Jul 2021 2 repositories listed Syntology ran 1 of 10 samples · 9 unverified
  We present Long Short-term TRansformer (LSTR), a temporal modeling algorithm for online action detection, which employs a long- and short-term memory mechanism to model prolonged sequence data.
• GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
  30 Jun 2020 2 repositories listed Syntology ran 9 of 10 samples · 1 unverified · 1 pointer-only (licence)
  Neural network scaling has been critical for improving the model quality in many real-world machine learning applications with vast amounts of training data and compute.
• Perceptual Similarity for Measuring Decision-Making Style and Policy Diversity in Games
  12 Aug 2024 1 repository listed
  Defining and measuring decision-making styles, also known as playstyles, is crucial in gaming, where these styles reflect a broad spectrum of individuality and diversity.
• PFGM++: Unlocking the Potential of Physics-Inspired Generative Models
  8 Feb 2023 1 repository listed Syntology ran 2 of 3 samples · 1 unverified · 3 pointer-only (licence)
  The new models reduce to PFGM when D=1 and to diffusion models when D→∞.
• On Reinforcement Learning for the Game of 2048
  21 Dec 2022 1 repository listed
  Furthermore, based on this approach, a state-of-the-art program for 2048 is developed, which achieves the highest performance among all learning-based programs, namely an average score of 625377 points and a rate of 72%…
• Parallel Context Windows for Large Language Models
  21 Dec 2022 1 repository listed Syntology ran 0 of 4 samples · 4 unverified
  We present Parallel Context Windows (PCW), a method that alleviates the context window restriction for any off-the-shelf LLM without further training.
• Pavementscapes: a large-scale hierarchical image dataset for asphalt pavement damage segmentation
  24 Jul 2022 1 repository listed
  However, few current public datasets limit the potential exploration of deep learning in the application of pavement damage segmentation.
• Efficient Human Pose Estimation via 3D Event Point Cloud
  9 Jun 2022 1 repository listed Syntology ran 4 of 8 samples · 4 unverified
  We then leverage the rasterized event point cloud as input to three different backbones, PointNet, DGCNN, and Point Transformer, with two linear layer decoders to predict the location of human keypoints.
• Characterizing the Efficiency vs. Accuracy Trade-off for Long-Context NLP Models
  15 Apr 2022 1 repository listed
  In this work, we perform a systematic study of this accuracy vs.
• Reconstruction of Perceived Images from fMRI Patterns and Semantic Brain Exploration using Instance-Conditioned GANs
  25 Feb 2022 1 repository listed Syntology ran 0 of 1 samples · 1 unverified
  Reconstructing perceived natural images from fMRI signals is one of the most engaging topics of neural decoding research.
• Optimistic Temporal Difference Learning for 2048
  22 Nov 2021 1 repository listed
  Our experiments show that both TD and TC learning with OI significantly improve the performance.
• Playing 2048 With Reinforcement Learning
  20 Oct 2021 1 repository listed
  The game of 2048 is a highly addictive game.
• Faster Person Re-Identification
  16 Aug 2020 1 repository listed
  In this work, we introduce a new solution for fast ReID by formulating a novel Coarse-to-Fine (CtF) hashing code search strategy, which complementarily uses short and long codes, achieving both faster speed and better…
• Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching
  26 Apr 2020 1 repository listed
  In order to better capture sentence level semantic relations within a document, we pre-train the model with a novel masked sentence block language modeling task in addition to the masked word language modeling task used…
• MG-WFBP: Merging Gradients Wisely for Efficient Communication in Distributed Deep Learning
  18 Dec 2019 1 repository listed
  Distributed synchronous stochastic gradient descent has been widely used to train deep neural networks (DNNs) on computer clusters.
• Scaling Distributed Training of Flood-Filling Networks on HPC Infrastructure for Brain Mapping
  13 May 2019 1 repository listed
  Mapping all the neurons in the brain requires automatic reconstruction of entire cells from volume electron microscopy data.
• Decoder-tailored Polar Code Design Using the Genetic Algorithm
  28 Jan 2019 1 repository listed
  We propose a new framework for constructing polar codes (i.
• Genetic Algorithm-based Polar Code Construction for the AWGN Channel
  19 Jan 2019 1 repository listed
  We propose a new polar code construction framework (i.
• Improving Electron Micrograph Signal-to-Noise with an Atrous Convolutional Encoder-Decoder
  30 Jul 2018 1 repository listed
  Our neural network was trained end-to-end to remove Poisson noise applied to low-dose (≪ 300 counts ppx) micrographs created from a new dataset of 17267 2048×2048 high-dose (> 2500 counts ppx) micrographs and then…
• Distributed Deep Reinforcement Learning: Learn how to play Atari games in 21 minutes
  9 Jan 2018 1 repository listed
  We present a study in Distributed Deep Reinforcement Learning (DDRL) focused on scalability of a state-of-the-art Deep Reinforcement Learning algorithm known as Batch Asynchronous Advantage ActorCritic (BA3C).
• ImageNet Training in Minutes
  14 Sep 2017 1 repository listed
  If we can make full use of the supercomputer for DNN training, we should be able to finish the 90-epoch ResNet-50 training in one minute.

Syntology lines on 8 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.