PyPI page
Home page
Author:
Fawz Mehfil
Summary:
A deterministic two-agent reinforcement-learning benchmark for a finite stranded-island economy.
Latest version:
0.1.0
Required dependencies:
fastapi
|
gymnasium
|
numpy
|
pettingzoo
|
pydantic
|
uvicorn
Optional dependencies:
httpx
|
jsonschema
|
mypy
|
pytest
|
ruff
|
tensorflow
Downloads last day:
2
Downloads last week:
9
Downloads last month:
19
7-day smoothing