Stable Baselines3SAFE

Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: stable-baselines3
description: Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.
license: MIT license
metadata:
    skill-author: K-Dense Inc.
---

# Stable Baselines3

## Routing Boundary

Use this skill only for Stable-Baselines3, SB3, PPO/SAC/DQN, reinforcement learning agents, Gymnasium environments, policies, rollouts, and RL training workflows. Do not use it for ordinary scikit-learn, random forests, supervised classification, tabular regression, or generic machine-learning model training.

## 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
- The replay buffer is NOT saved with the model to save space

**Algorithm Selection:**
Use `references/algorithms.md` for detailed algorithm characteristics and selection guidance. Quick reference:
- **PPO/A2C**: General-purpose, supports all action space types, good for multiprocessing
- **SAC/TD3**: Continuous control, off-policy, sample-efficient
- **DQN**: Discrete actions, off-policy
- **HER**: Goal-conditioned tasks

See `scripts/train_rl_agent.py` for a complete training template with best practices.

### 2. Custom Environments

**Requirements:**
Custom environments must inherit from `gymnasium.Env` and implement:
- `__init__()`: Define action_space and observation_space
- `reset(seed, options)`: Return initial observation and info dict
- `step(action)`: Return observation, reward, terminated, truncated, info
- `render()`: Visualization (optional)
- `close()`: Cleanup resources

**Key Constraints:**
- Image observations must be `np.uint8` in range [0, 255]
- Use channel-first format when possible (channels, height, width)
- SB3 normalizes images automatically by dividing by 255
- Set `normalize_images=False` in policy_kwargs if pre-normalized
- SB3 does NOT support `Discrete` or `MultiDiscrete` spaces with `start!=0`

**Validation:**
```python
from stable_baselines3.common.env_checker import check_env

check_env(env, warn=True)
```

See `scripts/custom_env_template.py` for a complete custom environment template and `references/custom_environments.md` for comprehensive guidance.

### 3. Vectorized Environments

**Purpose:**
Vectorized environments run multiple environment instances in parallel, accelerating training and enabling certain wrappers (frame-stacking, normalization).

**Types:**
- **DummyVecEnv**: Sequential execution on current process (for lightweight environments)
- **SubprocVecEnv**: Parallel execution across processes (for compute-heavy environments)

**Quick Setup:**
```python
from stable_baselines3.common.env_util import make_vec_env

# Create 4 parallel environments
env = make_vec_env("CartPole-v1", n_envs=4, vec_env_cls=SubprocVecEnv)

model = PPO("MlpPolicy", env, verbose=1)
model.learn(total_timesteps=25000)
```

**Off-Policy Optimization:**
When using multiple environments with off-policy algorithms (SAC, TD3, DQN), set `gradient_steps=-1` to perform one gradient update per environment step, balancing wall-clock time and sample efficiency.

**API Differences:**
- `reset()` returns only observations (info available in `vec_env.reset_infos`)
- `step()` returns 4-tuple: `(obs, rewards, dones, infos)` not 5-tuple
- Environments auto-reset after episodes
- Terminal observations available via `infos[env_idx]["terminal_observation"]`

See `references/vectorized_envs.md` for detailed information on wrappers and advanced usage.

### 4. Callbacks for Monitoring and Control

**Purpose:**
Callbacks enable monitoring metrics, saving checkpoints, implementing early stopping, and custom training logic without modifying core algorithms.

**Common Callbacks:**
- **EvalCallback**: Evaluate periodically and save best model
- **CheckpointCallback**: Save model checkpoints at intervals
- **StopTrainingOnRewardThreshold**: Stop when target reward reached
- **ProgressBarCallback**: Display training progress with timing

**Custom Callback Structure:**
```python
from stable_baselines3.common.callbacks import BaseCallback

class CustomCallback(BaseCallback):
    def _on_training_start(self):
        # Called before first rollout
        pass

    def _on_step(self):
        # Called after each environment step
        # Return False to stop training
        return True

    def _on_rollout_end(self):
        # Called at end of rollout
        pass
```

**Available Attributes:**
- `self.model`: The RL algorithm instance
- `self.num_timesteps`: Total environment steps
- `self.training_env`: The training environment

**Chaining Callbacks:**
```python
from stable_baselines3.common.callbacks import CallbackList

callback = CallbackList([eval_callback, checkpoint_callback, custom_callback])
model.learn(total_timesteps=10000, callback=callback)
```

See `references/callbacks.md` for comprehensive callback documentation.

### 

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.