OpenCodePapers

atari-games-on-atari-100k

Atari Games
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeMedian Human Normalized ScoreMean Human Normalized ScoreModelNameReleaseDate
EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data✓ Link128.6242.8EfficientZero V22024-03-01
Mastering Atari Games with Limited Data✓ Link109.0194.3EfficientZero2021-10-30
Uncovering Untapped Potential in Sample-Efficient World Model Agents✓ Link98.2164.5Simulus2025-02-17
Bigger, Better, Faster: Human-level Atari with human-level efficiency✓ Link91.7224.7BBF2023-05-30
EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling82187EDELINE2025-02-01
Learning to Play Atari in a World of Tokens✓ Link79.0102.2DART2024-06-03
From Observations to Events: Event-Aware World Models for Reinforcement Learning✓ Link77.3181.8EASimulus2026-01-27
Learning Transformer-based World Models with Contrastive Predictive Coding✓ Link77162TWISTER2025-03-06
GLAM: Global-Local Variation Awareness in Mamba-based World Model✓ Link61.8130.6GLAM2025-01-21
STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning58.4126.7STORM2023-10-14
Transformer-based World Models Are Happy With 100k Interactions✓ Link50.595.6TWM2023-03-13
Objects matter: object-centric world models improve reinforcement learning in visually complex environments✓ Link43.8134.8OC-STORM2025-01-27
Data-Efficient Reinforcement Learning with Self-Predictive Representations✓ Link41.570.4SPR2020-07-12
Diffusion for World Modeling: Visual Details Matter in Atari✓ Link37.3145.9DIAMOND2024-05-20
Transformers are Sample-Efficient World Models✓ Link28.9104.6IRIS2023-03-01
Improving Token-Based World Models with Parallel Observation Prediction✓ Link28.0122.2REM2024-02-08
Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels✓ Link26.8Efficient DQN + DrQ2020-04-28
CURL: Contrastive Unsupervised Representations for Reinforcement Learning✓ Link17.538.1CURL2020-04-08
Check out how to contribute new results. Then edit this file on GitLab or GitHub.