FOUNDER maps foundation-model embeddings of text or video prompts into world-model goal states and rewards policies by predicted temporal distance to those goals, improving reward-free multi-task offline control.
Guiding pretraining in reinforcement learning with large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making
FOUNDER maps foundation-model embeddings of text or video prompts into world-model goal states and rewards policies by predicted temporal distance to those goals, improving reward-free multi-task offline control.