PyPI page
Home page
Author:
Maximilian König
Summary:
In-Context Reinforcement Learning framework for LLMs — no fine-tuning required.
Latest version:
1.1.2
Required dependencies:
agno
|
pyyaml
|
tqdm
Optional dependencies:
ollama
|
openai
Downloads last day:
0
Downloads last week:
28
Downloads last month:
26
7-day smoothing