Skill · em Dados, IA e pesquisa

stable-baselines3

Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating custom Gym environments, implementing callbacks for monitoring and control, using vectorized environments for parallel training, and integrating with deep RL workflows. This…

Procedência

Origem: davila7/claude-code-templates
Caminho: cli-tool/components/skills/scientific/stable-baselines3
Versão fixada: 57f899e5394bb8ca166f38eacae8f0853cbfe033
Licença: MIT
Espelhado em 25/09/2026
1 download no Claude Code Templates (lido em 25/09/2026)

Antes de instalar

8 arquivos · 83,5 KB · inclui 3 scripts que executam: scripts/custom_env_template.py, scripts/evaluate_agent.py, scripts/train_rl_agent.py

Instalar na sua CLI

O comando baixa a versão fixada (commit 57f899e) direto da origem, para a pasta que a CLI lê. Precisa de curl (macOS e Linux); no Windows não há comando, porque o Rook Labs é para macOS.

Claude Code

Neste projeto: instala em .claude/skills/stable-baselines3/.

d=".claude/skills/stable-baselines3"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/scientific/stable-baselines3"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/algorithms.md" "$u/references/algorithms.md" \
  -o "$d/references/callbacks.md" "$u/references/callbacks.md" \
  -o "$d/references/custom_environments.md" "$u/references/custom_environments.md" \
  -o "$d/references/vectorized_envs.md" "$u/references/vectorized_envs.md" \
  -o "$d/scripts/custom_env_template.py" "$u/scripts/custom_env_template.py" \
  -o "$d/scripts/evaluate_agent.py" "$u/scripts/evaluate_agent.py" \
  -o "$d/scripts/train_rl_agent.py" "$u/scripts/train_rl_agent.py" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Global: instala em ~/.claude/skills/stable-baselines3/.

d="$HOME/.claude/skills/stable-baselines3"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/scientific/stable-baselines3"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/algorithms.md" "$u/references/algorithms.md" \
  -o "$d/references/callbacks.md" "$u/references/callbacks.md" \
  -o "$d/references/custom_environments.md" "$u/references/custom_environments.md" \
  -o "$d/references/vectorized_envs.md" "$u/references/vectorized_envs.md" \
  -o "$d/scripts/custom_env_template.py" "$u/scripts/custom_env_template.py" \
  -o "$d/scripts/evaluate_agent.py" "$u/scripts/evaluate_agent.py" \
  -o "$d/scripts/train_rl_agent.py" "$u/scripts/train_rl_agent.py" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Codex

Neste projeto: instala em .agents/skills/stable-baselines3/.

d=".agents/skills/stable-baselines3"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/scientific/stable-baselines3"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/algorithms.md" "$u/references/algorithms.md" \
  -o "$d/references/callbacks.md" "$u/references/callbacks.md" \
  -o "$d/references/custom_environments.md" "$u/references/custom_environments.md" \
  -o "$d/references/vectorized_envs.md" "$u/references/vectorized_envs.md" \
  -o "$d/scripts/custom_env_template.py" "$u/scripts/custom_env_template.py" \
  -o "$d/scripts/evaluate_agent.py" "$u/scripts/evaluate_agent.py" \
  -o "$d/scripts/train_rl_agent.py" "$u/scripts/train_rl_agent.py" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Global: instala em ~/.agents/skills/stable-baselines3/.

d="$HOME/.agents/skills/stable-baselines3"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/scientific/stable-baselines3"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/algorithms.md" "$u/references/algorithms.md" \
  -o "$d/references/callbacks.md" "$u/references/callbacks.md" \
  -o "$d/references/custom_environments.md" "$u/references/custom_environments.md" \
  -o "$d/references/vectorized_envs.md" "$u/references/vectorized_envs.md" \
  -o "$d/scripts/custom_env_template.py" "$u/scripts/custom_env_template.py" \
  -o "$d/scripts/evaluate_agent.py" "$u/scripts/evaluate_agent.py" \
  -o "$d/scripts/train_rl_agent.py" "$u/scripts/train_rl_agent.py" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Antigravity

Neste projeto: instala em .agents/skills/stable-baselines3/.

d=".agents/skills/stable-baselines3"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/scientific/stable-baselines3"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/algorithms.md" "$u/references/algorithms.md" \
  -o "$d/references/callbacks.md" "$u/references/callbacks.md" \
  -o "$d/references/custom_environments.md" "$u/references/custom_environments.md" \
  -o "$d/references/vectorized_envs.md" "$u/references/vectorized_envs.md" \
  -o "$d/scripts/custom_env_template.py" "$u/scripts/custom_env_template.py" \
  -o "$d/scripts/evaluate_agent.py" "$u/scripts/evaluate_agent.py" \
  -o "$d/scripts/train_rl_agent.py" "$u/scripts/train_rl_agent.py" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Global: instala em ~/.gemini/antigravity-cli/skills/stable-baselines3/.

d="$HOME/.gemini/antigravity-cli/skills/stable-baselines3"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/scientific/stable-baselines3"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/algorithms.md" "$u/references/algorithms.md" \
  -o "$d/references/callbacks.md" "$u/references/callbacks.md" \
  -o "$d/references/custom_environments.md" "$u/references/custom_environments.md" \
  -o "$d/references/vectorized_envs.md" "$u/references/vectorized_envs.md" \
  -o "$d/scripts/custom_env_template.py" "$u/scripts/custom_env_template.py" \
  -o "$d/scripts/evaluate_agent.py" "$u/scripts/evaluate_agent.py" \
  -o "$d/scripts/train_rl_agent.py" "$u/scripts/train_rl_agent.py" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Peça ao Rook

Já usa o Rook Labs? Cole no chat do Rook: instale a skill https://rooklabs.sh/marketplace/cct.stable-baselines3

Prévia do SKILL.md

---
name: stable-baselines3
description: Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating custom Gym environments, implementing callbacks for monitoring and control, using vectorized environments for parallel training, and integrating with deep RL workflows. This skill sh…
---

# Stable Baselines3

## Overview

Stable Baselines3 (SB3) is a PyTorch-based library providing reliable implementations of reinforcement learning algorithms. This skill provides comprehensive guidance for training RL agents, creating custom environments, implementing callbacks, and optimizing training workflows using SB3's unified API.

## Core Capabilities

### 1. Training RL Agents

**Basic Training Pattern:**

```python
import gymnasium as gym
from stable_baselines3 import PPO

# Create environment
env = gym.make("CartPole-v1")

# Initialize agent
model = PPO("MlpPolicy", env, verbose=1)

# Train the agent
model.learn(total_timesteps=10000)

# Save the model
model.save("ppo_cartpole")

# Load the model (without prior instantiation)
model = PPO.load("ppo_cartpole", env=env)
```

**Important Notes:**
- `total_timesteps` is a lower bound; actual training may exceed this due to batch collection
- Use `model.load()` as a static method, not on an existing instance
…

Ver todo o marketplace