Agente RL com Aprendizado Adaptativo
SumanMadipeddi/RL_Environment_Training
Agent com RL para otimizar comportamento via feedback adaptativo
Ver no GitHubAgent que interage com ambientes de aprendizado por reforço, usando ferramentas da Anthropic para adaptar comportamento e melhorar performance iterativamente. Referencia SWE-Bench Pro para avaliar capacidades de engenharia de software em ciclos de treinamento.
Instalação
npx convez-ai SumanMadipeddi/RL_Environment_Training1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Treinar agents a resolver problemas de engenharia de software
- Iterar políticas de IA com feedback de ambiente
- Avaliar melhoria de performance em tarefas complexas
Veredito

Projeto técnico sólido para quem quer explorar aprendizado por reforço com Claude. Bem estruturado com setup claro, mas requer conhecimento em RL e Python avançado para customização real.
README
A tradução para o português deste README ainda está na fila.
This is my personal repo for RL environment engineering. I’m iterating on an agent that interacts with a custom RL-style environment and uses Anthropic tools to adapt behavior over time.
Project goals
- The initial policy/agent should intentionally fail about 60% of the time (i.e., succeed roughly 40%) to ensure the environment is challenging and informative.
- Over repeated interactions, the agent should learn and demonstrate improvement, achieving the targeted behavior with number of repetitions.
Prerequisites
-
- Git (latest)
- Python 3.11+ (see
.python-versionfor the exact version) - uv for Python project management (
pip install uvor seehttps://docs.astral.sh/uv/) - An Anthropic API key
Setup (Windows PowerShell)
- Clone and enter the repo
git clone <repo-url>
- Install dependencies with uv
uv sync
- Set your Anthropic API key in the current shell
$env:ANTHROPIC_API_KEY="your_api_key_here"
- Run the agent
uv run main.py
Execution Modes
The agent can run tests concurrently or sequentially. Change the concurrent flag at the bottom of main.py:
asyncio.run(main(concurrent=True))
asyncio.run(main(concurrent=False))
When running concurrently, results print as they complete (not in run order) for faster overall execution.
Benchmark reference
This project references and draws inspiration from large-scale software engineering benchmarks such as SWE-Bench Pro. For details about the dataset, task structure, and evaluation setup, see the dataset page on Hugging Face: ScaleAI/SWE-bench_Pro.