SOTAVerified

Playing the Game of 2048

Papers

Showing 1–25 of 57 papers

TitleStatusHype
PFGM++: Unlocking the Potential of Physics-Inspired Generative ModelsCode2
Train Short, Test Long: Attention with Linear Biases Enables Input Length ExtrapolationCode2
GSPMD: General and Scalable Parallelization for ML Computation GraphsCode2
On Reinforcement Learning for the Game of 2048Code1
Parallel Context Windows for Large Language ModelsCode1
Pavementscapes: a large-scale hierarchical image dataset for asphalt pavement damage segmentationCode1
Efficient Human Pose Estimation via 3D Event Point CloudCode1
Reconstruction of Perceived Images from fMRI Patterns and Semantic Brain Exploration using Instance-Conditioned GANsCode1
Optimistic Temporal Difference Learning for 2048Code1
Planning in Stochastic Environments with a Learned ModelCode1
Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image HarmonizationCode1
Long Short-Term Transformer for Online Action DetectionCode1
Faster Person Re-IdentificationCode1
Perceptual Similarity for Measuring Decision-Making Style and Policy Diversity in GamesCode0
Rapid Person Re-Identification via Sub-space Consistency Regularization—0
You Can't Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments—0
Characterizing the Efficiency vs. Accuracy Trade-off for Long-Context NLP ModelsCode0
Pathways: Asynchronous Distributed Dataflow for ML—0
The Economics of Orbit Use: Open Access, External Costs, and Runaway Debris Growth—0
DVHN: A Deep Hashing Framework for Large-scale Vehicle Re-identification—0
Playing 2048 With Reinforcement LearningCode0
Why Out-of-distribution Detection in CNNs Does Not Like Mahalanobis -- and What to Use Instead—0
Scalable Reverse Image Search Engine for NASAWorldview—0
Accelerating Markov Random Field Inference with Uncertainty Quantification—0
M6-T: Exploring Sparse Expert Models and Beyond—0
Show:102550
← PrevPage 1 of 3Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Stochastic MuzeroAverage Score500,000—Unverified
2AlphaZero (With Simulator)Average Score500,000—Unverified
3MuZeroAverage Score300,000—Unverified
4Beam SearchAverage Score1,024—Unverified
5DQN (1000 episodes)Average Score256—Unverified