playing-games-2

Playing the Game of 2048

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in playing-the-game-of-2048-2

Trend

Dataset

Best Model

Actions

The Game of 2048

Libraries

i

Use these libraries to find playing-the-game-of-2048-2 models and implementations

Datasets

The Game of 2048

Subtasks

No subtasks available.

Most implemented papers

Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

Noah A. Smith, M. Lewis, Ofir Press•Thu Aug 26 2021

This work shows that extrapolation can be enabled by simply changing the position representation method, though it finds that current methods do not allow for efficient extrapolation, and introduces a simpler and more efficient position method, Attention with Linear Biases (ALiBi).

1050

Content

0

Paper Graph

GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding

M. Krikun, Orhan Firat, Dmitry Lepikhin, HyoukJoong Lee, Yuanzhong Xu, Dehao Chen, Yanping Huang, Noam Shazeer, Z. Chen•Mon Jun 29 2020

GShard enabled us to scale up multilingual neural machine translation Transformer model with Sparsely-Gated Mixture-of-Experts beyond 600 billion parameters using automatic sharding and it is demonstrated that such a giant model can efficiently be trained on 2048 TPU v3 accelerators in 4 days to achieve far superior quality for translation from 100 languages to English compared to the prior art.

1534 0

Paper Graph

Mastering 2048 With Delayed Temporal Coherence Learning, Multistage Weight Promotion, Redundant Encoding, and Carousel Shaping

Wojciech Jaśkowski•Sun Apr 17 2016

The best known 2048 playing program is developed, which confirms the effectiveness of the introduced methods for discrete-state Markov decision problems, with the aim to develop a strong playing program.

31 0

Paper Graph

Long Short-Term Transformer for Online Action Detection

Yuanjun Xiong, Z. Tu, S. Soatto, Mingze Xu, Hao Chen, Xinyu Li, Wei Xia•Tue Jul 06 2021

LSTR provides an effective and efficient method to model long videos with fewer heuristics, which is validated by extensive empirical analysis and achieves state-of-the-art performance on three standard online action detection benchmarks.

172 0

Paper Graph

Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization

Chi-Man Pun, Xiaodong Cun, Jing Liang•Sun Sep 12 2021

A novel spatial-separated curve rendering network for efficient and high-resolution image harmonization for the first time and reduces more than 90% parameters compared with previous methods but still achieves the state-of-the-art performance on both synthesized iHarmony4 and real-world DIH test sets.

48 0

Paper Graph

Planning in Stochastic Environments with a Learned Model

Julian Schrittwieser, David Silver, Ioannis Antonoglou, Sherjil Ozair, Thomas K. Hubert•Fri Dec 31 2021

A new algorithm is introduced, Stochastic MuZero, that learns a stochastic model incorporating afterstates, and uses this model to perform a stochastic tree search and maintain the superhuman performance of standard MuZero in the game of Go.

73 0

Paper Graph

ImageNet Training in Minutes

K. Keutzer, Yang You, J. Demmel, Cho-Jui Hsieh, Zhao Zhang•Wed Sep 13 2017

This paper empirically evaluates the effectiveness on two neural networks: AlexNet and ResNet-50 trained with the ImageNet-1k dataset while preserving the state-of-the-art test accuracy, and uses large batch size, powered by the Layer-wise Adaptive Rate Scaling (LARS) algorithm, for efficient usage of massive computing resources.

464 0

Paper Graph

Distributed Deep Reinforcement Learning: Learn how to play Atari games in 21 minutes

H. Michalewski, Igor Adamski, R. Adamski, T. Grel, Adam Jedrych, Kamil Kaczmarek•Mon Jan 08 2018

This study shows that using the Adam optimization algorithm with a batch size of up to 2048 is a viable choice for carrying out large scale machine learning computations.

37 0

Paper Graph

Genetic Algorithm-based Polar Code Construction for the AWGN Channel

Sebastian Cammerer, S. Brink, Ahmed Elkelesh, Moustafa Ebada•Fri Jan 18 2019

A belief propagation-tailored polar code approaches the SCL error-rate performance without any modifications in the decoding algorithm itself, based on the Genetic Algorithm.

13 0

Paper Graph

Improving electron micrograph signal-to-noise with an atrous convolutional encoder-decoder.

Jeffrey M. Ede, R. Beanland•Sun Jun 30 2019

An atrous convolutional encoder-decoder trained to denoise electron micrographs and outperforms their best mean squared error and structural similarity index performances.

32 0

Paper Graph

Adding a benchmark result helps the community track progress.