Image de couverture de livre

Probing the Impact of Scale on Data-Efficient, Generalist Transformer World Models for Atari

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Kim, Jooyeon
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning
par: Delfosse, Quentin, et autres
Publié: (2024)

Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection
par: Fan, Jiajun, et autres
Publié: (2023)

Diffusion for World Modeling: Visual Details Matter in Atari
par: Alonso, Eloi, et autres
Publié: (2024)

Hadamax Encoding: Elevating Performance in Model-Free Atari
par: Kooi, Jacob E., et autres
Publié: (2025)

Decision Transformer vs. Decision Mamba: Analysing the Complexity of Sequential Decision Making in Atari Games
par: Yan, Ke
Publié: (2024)

Improving Transformer World Models for Data-Efficient RL
par: Dedieu, Antoine, et autres
Publié: (2025)

Scaling Generalist Data-Analytic Agents
par: Qiao, Shuofei, et autres
Publié: (2025)

Inference-Time Scaling for Generalist Reward Modeling
par: Liu, Zijun, et autres
Publié: (2025)

Learning To Play Atari Games Using Dueling Q-Learning and Hebbian Plasticity
par: Salehin, Md Ashfaq
Publié: (2024)

MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games
par: Wu, Ti-Rong, et autres
Publié: (2023)

A quantum-classical reinforcement learning model to play Atari games
par: Freinberger, Dominik, et autres
Publié: (2024)

TextAtari: 100K Frames Game Playing with Language Agents
par: Li, Wenhao, et autres
Publié: (2025)

Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals
par: Wu, Yue, et autres
Publié: (2023)

Enhancing Two-Player Performance Through Single-Player Knowledge Transfer: An Empirical Study on Atari 2600 Games
par: Saadat, Kimiya, et autres
Publié: (2024)

The Impact of Off-Policy Training Data on Probe Generalisation
par: Kirch, Nathalie, et autres
Publié: (2025)

DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
par: Gao, Shenyuan, et autres
Publié: (2026)

Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective
par: Fang, Yuchen, et autres
Publié: (2024)

RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots
par: Nasiriany, Soroush, et autres
Publié: (2024)

OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments
par: Delfosse, Quentin, et autres
Publié: (2023)

From Generalist to Specialist Representation
par: Zheng, Yujia, et autres
Publié: (2026)

LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence
par: Zhang, Xingxuan, et autres
Publié: (2025)

ControlMath: Controllable Data Generation Promotes Math Generalist Models
par: Chen, Nuo, et autres
Publié: (2024)

Improving World Models using Deep Supervision with Linear Probes
par: Zahorodnii, Andrii
Publié: (2025)

Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism
par: Jiang, Yuhua, et autres
Publié: (2025)

Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performance
par: Grosnit, Antoine, et autres
Publié: (2024)

Random Conditioning with Distillation for Data-Efficient Diffusion Model Compression
par: Kim, Dohyun, et autres
Publié: (2025)

RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots
par: Nasiriany, Soroush, et autres
Publié: (2026)

Scaling Sequential Recommendation Models with Transformers
par: Zivic, Pablo, et autres
Publié: (2024)

Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers
par: Kim, Junhan, et autres
Publié: (2024)

TA-GGAD: Testing-time Adaptive Graph Model for Generalist Graph Anomaly Detection
par: Zhang, Xiong, et autres
Publié: (2026)

What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models
par: Vafa, Keyon, et autres
Publié: (2025)

CoScale-RL: Efficient Post-Training by Co-Scaling Data and Computation
par: Chen, Yutong, et autres
Publié: (2026)

Transformers Linearly Represent Highly Structured World Models
par: Kniazev, Roman, et autres
Publié: (2026)

Diffusion Transformers as Open-World Spatiotemporal Foundation Models
par: Yuan, Yuan, et autres
Publié: (2024)

Scaling Laws for Pre-training Agents and World Models
par: Pearce, Tim, et autres
Publié: (2024)

Scaling Laws for Data-Efficient Visual Transfer Learning
par: Yang, Wenxuan, et autres
Publié: (2025)

Generalist Foundation Models Are Not Clinical Enough for Hospital Operations
par: Jiang, Lavender Y., et autres
Publié: (2025)

ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-Variable Context Encoding
par: Gudovskiy, Denis, et autres
Publié: (2024)

MMET: A Multi-Input and Multi-Scale Transformer for Efficient PDEs Solving
par: Luo, Yichen, et autres
Publié: (2025)

Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models
par: Zhang, Yang, et autres
Publié: (2024)