A 3B LLM post-trained with MS-GRPO, which gives every step the episode's total reward and samples high-advantage episodes, beats a 72B baseline on Frozen Lake but is inconsistent on Snake.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reinforced Language Models for Sequential Decision Making
A 3B LLM post-trained with MS-GRPO, which gives every step the episode's total reward and samples high-advantage episodes, beats a 72B baseline on Frozen Lake but is inconsistent on Snake.