AGENT SKILL

stable-baselines3

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 许可
MIT
最近更新
2026-10-22
Stars
★ 0
Forks
0

01 前言 Front Matter

name
stable-baselines3
license
MIT license
metadata
{ "version": "1.1", "skill-author": "K-Dense Inc." }
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.
allowed-tools
Read Write Edit Bash
compatibility
Requires Python 3.10+, PyTorch >= 2.3, and stable-baselines3 2.8+. Gymnasium environments; optional extras for TensorBoard and Atari (ale-py).

02 资源文件 7

03 SKILL.md 正文

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.

Current upstream: SB3 2.8.0 (April 2026). Docs: stable-baselines3.readthedocs.io.

Installation

Tested against stable-baselines3 2.8.0. Requires Python 3.10+ (3.9 dropped in 2.8.0) and PyTorch >= 2.3.

# Basic installation
uv pip install "stable-baselines3>=2.8"

# With extra dependencies (TensorBoard, ale-py for Atari, etc.)
uv pip install "stable-baselines3[extra]>=2.8"

On zsh, quote brackets: uv pip install 'stable-baselines3[extra]>=2.8'.

For MuJoCo continuous-control benchmarks:

uv pip install "gymnasium[mujoco]"

Check your version:

import stable_baselines3
print(stable_baselines3.__version__)

Related Projects

  • SB3-Contrib: experimental algorithms (MaskablePPO, CrossQ, QR-DQN, RecurrentPPO) — separate sb3-contrib package
  • RL Baselines3 Zoo: pre-trained agents, hyperparameters, training scripts
  • SBX: SB3 + JAX implementations for users who prefer JAX over PyTorch

Core Capabilities

1. Training RL Agents

Basic Training Pattern:

import gymnasium as gym
from stable_baselines3 import PPO

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

# Initialize agent (device="cpu" is often faster for MlpPolicy on small envs)
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:

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:

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:

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:

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.

5. Model Persistence and Inspection

Saving and Loading:

# Save model
model.save("model_name")

# Save normalization statistics (if using VecNormalize)
vec_env.save("vec_normalize.pkl")

# Load model
model = PPO.load("model_name", env=env)

# Load normalization statistics
vec_env = VecNormalize.load("vec_normalize.pkl", vec_env)

Parameter Access:

# Get parameters
params = model.get_parameters()

# Set parameters
model.set_parameters(params)

# Access PyTorch state dict
state_dict = model.policy.state_dict()

6. Evaluation and Recording

Evaluation:

from stable_baselines3.common.evaluation import evaluate_policy

mean_reward, std_reward = evaluate_policy(
    model,
    env,
    n_eval_episodes=10,
    deterministic=True
)

Video Recording:

from stable_baselines3.common.vec_env import VecVideoRecorder

# Wrap environment with video recorder
env = VecVideoRecorder(
    env,
    "videos/",
    record_video_trigger=lambda x: x % 2000 == 0,
    video_length=200
)

See scripts/evaluate_agent.py for a complete evaluation and recording template.

7. Advanced Features

Learning Rate Schedules:

def linear_schedule(initial_value):
    def func(progress_remaining):
        # progress_remaining goes from 1 to 0
        return progress_remaining * initial_value
    return func

model = PPO("MlpPolicy", env, learning_rate=linear_schedule(0.001))

Multi-Input Policies (Dict Observations):

model = PPO("MultiInputPolicy", env, verbose=1)

Use when observations are dictionaries (e.g., combining images with sensor data).

Hindsight Experience Replay:

from stable_baselines3 import SAC, HerReplayBuffer

model = SAC(
    "MultiInputPolicy",
    env,
    replay_buffer_class=HerReplayBuffer,
    replay_buffer_kwargs=dict(
        n_sampled_goal=4,
        goal_selection_strategy="future",
    ),
)

TensorBoard Integration:

model = PPO("MlpPolicy", env, tensorboard_log="./tensorboard/")
model.learn(total_timesteps=10000)

Workflow Guidance

Starting a New RL Project:

  1. Define the problem: Identify observation space, action space, and reward structure
  2. Choose algorithm: Use references/algorithms.md for selection guidance
  3. Create/adapt environment: Use scripts/custom_env_template.py if needed
  4. Validate environment: Always run check_env() before training
  5. Set up training: Use scripts/train_rl_agent.py as starting template
  6. Add monitoring: Implement callbacks for evaluation and checkpointing
  7. Optimize performance: Consider vectorized environments for speed
  8. Evaluate and iterate: Use scripts/evaluate_agent.py for assessment

Common Issues:

  • Memory errors: Reduce buffer_size for off-policy algorithms or use fewer parallel environments
  • Slow training: Consider SubprocVecEnv for parallel environments
  • Unstable training: Try different algorithms, tune hyperparameters, or check reward scaling
  • Import errors: Ensure stable_baselines3 is installed: uv pip install 'stable-baselines3[extra]>=2.8'

Resources

scripts/

  • train_rl_agent.py: Complete training script template with best practices
  • evaluate_agent.py: Agent evaluation and video recording template
  • custom_env_template.py: Custom Gym environment template

references/

  • algorithms.md: Detailed algorithm comparison and selection guide
  • custom_environments.md: Comprehensive custom environment creation guide
  • callbacks.md: Complete callback system reference
  • vectorized_envs.md: Vectorized environment usage and wrappers

04 同仓库更多 Skills

nikhilesh-s
nikhilesh-s/claude-toolkit

zarr-python

Chunked N-D arrays for cloud storage (Zarr-Python 3). Compressed arrays, parallel I/O, S3/GCS via fsspec, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.

★ 0
nikhilesh-s
nikhilesh-s/claude-toolkit

video-use

Edit any video by conversation. Transcribe, cut, color grade, generate overlay animations, burn subtitles — for talking heads, montages, tutorials, travel, interviews. No presets, no menus. Ask questions, confirm the plan, execute, iterate, persist. Production-correctness rules are hard; everything else is artistic freedom.

★ 0
nikhilesh-s
nikhilesh-s/claude-toolkit

venue-templates

Prepare journal manuscripts, conference papers, research posters, and grant documents using venue-specific formatting guidance and bundled LaTeX scaffolds. Use when selecting an official template, checking current page or anonymity rules, adapting academic writing to a venue, or inspecting a submission PDF.

★ 0
nikhilesh-s
nikhilesh-s/claude-toolkit

vaex

Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.

★ 0
nikhilesh-s
nikhilesh-s/claude-toolkit

usfiscaldata

Query the U.S. Treasury Fiscal Data REST API for federal financial data. No API key required. Use for national debt (Debt to the Penny), Daily Treasury Statements, Monthly Treasury Statements, Treasury securities auctions, interest rates, foreign exchange rates, savings bonds, or U.S. government revenue and spending statistics.

★ 0
nikhilesh-s
nikhilesh-s/claude-toolkit

uncertainty-and-units

Track physical units and propagate measurement uncertainty in scientific calculations using pint and uncertainties. Use for unit conversion and dimensional checking, GUM uncertainty budgets, Type A and Type B evaluation, coverage factors and expanded uncertainty, Monte Carlo propagation, significant-figure and plus-minus reporting, error propagation through curve fits, CODATA constants, auditing Python code for stripped units or broken uncertainty propagation, and order-of-magnitude plausibility checks using dimensionless groups (Reynolds, Peclet, Damkohler, Knudsen, Biot, Womersley), characteristic scales such as diffusion time or Debye length, and observed magnitude ranges. Trigger on "is this number physically reasonable", "sanity check these units", "what regime is this flow in", or a result that looks off by orders of magnitude.

★ 0