Skip to content

Instantly share code, notes, and snippets.

@quantra-go-algo

quantra-go-algo/step_6_from_policy_to_position_sizing_wi_1.py

Created June 24, 2026 01:29
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save quantra-go-algo/cc135143874eb247b37dce718ecdb032 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save quantra-go-algo/cc135143874eb247b37dce718ecdb032 to your computer and use it in GitHub Desktop.
Download ZIP
guardrailed-llm-agent — Step 6: From Policy to Position: Sizing with Volatility Targeting (snippet 1)
Raw
step_6_from_policy_to_position_sizing_wi_1.py
def action_to_base_exposure(action, size):
# Maps LLM output to a base exposure in [0.5, 1.0]. No shorts.
if action == 'LONG':
return LONG_FULL_EXP if size >= 1.0 else LONG_HALF_EXP # 1.0 or 0.8
return FLAT_EXP # 0.5: never fully exit
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment