A GPT-2-initialized Decision Transformer with LoRA matches or beats CQL, IQL, and BC on offline DJIA trading and generally beats a randomly initialized twin, though with weak statistical support.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-fin.CP 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Pretrained LLM Adapted with LoRA as a Decision Transformer for Offline RL in Quantitative Trading
A GPT-2-initialized Decision Transformer with LoRA matches or beats CQL, IQL, and BC on offline DJIA trading and generally beats a randomly initialized twin, though with weak statistical support.