PGT optimizes latent goal embeddings for frozen policies via trajectory-level preference objectives, reporting 72-81.6% relative gains on 17 Minecraft tasks and 13.4% better OOD performance than fine-tuning.
Describe, explain, plan and select: interactive planning with large language models enables open-world multi-task agents
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies
PGT optimizes latent goal embeddings for frozen policies via trajectory-level preference objectives, reporting 72-81.6% relative gains on 17 Minecraft tasks and 13.4% better OOD performance than fine-tuning.