GPT-J with full action history achieves 3.5x improvement over RL in ScienceWorld and matches a two-stage system using 29x larger models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Remember what you did so you know what to do next
GPT-J with full action history achieves 3.5x improvement over RL in ScienceWorld and matches a two-stage system using 29x larger models.