A direct endpoint-prediction world model trained on long-horizon objectives substantially beats recursively-rolled-out baselines, and the objective, not the backbone, drives the improvement.
Multi-timestep models for model-based reinforcement learning, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Beyond Myopic World Models: Long-Horizon End-to-End Training for Direct Future Prediction
A direct endpoint-prediction world model trained on long-horizon objectives substantially beats recursively-rolled-out baselines, and the objective, not the backbone, drives the improvement.