PyPI page
Home page
Author:
Philip Osborne
Summary:
Reinforcement Learning Bridge - connects LLMs to RL environments, automates language-based problem construction, and derives instructions for long-term goals without user supervision
Latest version:
0.1.4
Required dependencies:
fastapi
|
gymnasium
|
httpx
|
mcp
|
numpy
|
pillow
|
pydantic
|
rich
|
typer
|
uvicorn
Optional dependencies:
ale-py
|
build
|
gymnasium
|
hatchling
|
mypy
|
openai
|
pytest
|
pytest-asyncio
|
ruff
|
sentence-transformers
|
torch
|
twine
Downloads last day:
0
Downloads last week:
7
Downloads last month:
105