Beyond Myopic World Models: Long-Horizon End-to-End Training for Direct Future Prediction
Xinyi Li, Zaishuo Xia, Chenjie Hao, Yubei Chen
cs.LG
Submitted: 2026-08-07
Updated: 2026-08-10
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Lipschitz Continuity in Model-based Reinforcement Learning
- Combating the Compounding-Error Problem with a Multi-step Model
- Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
- Genie: Generative Interactive Environments
- Unsupervised Learning for Physical Interaction through Video Prediction
- World Models
- Dream to Control: Learning Behaviors by Latent Imagination
- Mastering Atari with Discrete World Models
- Temporal Difference Learning for Model Predictive Control
- TD-MPC2: Scalable, Robust World Models for Continuous Control
- Model-Based Planning with Discrete and Continuous Actions
- How Far is Video Generation from World Model: A Physical Law Perspective
- SmallWorlds: Assessing Dynamics Understanding of World Models in Isolated Environments
- From Kepler to Newton: Inductive Biases Guide Learned World Models in Transformers
- FiLM: Visual Reasoning with a General Conditioning Layer
- Self-Correcting Models for Model-Based Reinforcement Learning
- What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models
- Leveraging Jumpy Models for Planning and Fast Learning in Robotic Domains
- Hierarchical Planning with Latent World Models
- Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks