[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QG3D2FK4WNNFF7Z7TRQB83":3,"skill-same:01M6QG3D2FK4WNNFF7Z7TRQB83":111},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":14,"repositoryHtmlUrl":59,"repositoryHomepageUrl":60,"ownerHtmlUrl":61,"ownerBlogUrl":62,"ownerDescription":63,"updatedAt":64,"install":65,"resources":78},"01M6QG3D2FK4WNNFF7Z7TRQB83","stable-baselines3",null,"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.","Tashima-Tarsh\u002FDisha6.6","Tashima-Tarsh","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F269906498?v=4","01M6PBH98X03XERH0HFT4PFB1P","NITISH KUMAR","01M6PBH9DA0M6KM3Z12P848F0K",0,"MIT","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-stable-baselines3\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"stable baselines3","read","production-ready","quick","prototyping","data-science","high-performance","scikit-learn","ready","edit","write","performance","Bash","api","data","vectorized","learn","training","pytorch","experiments","2026-11-10 10:12:30",false,"---\nname: stable-baselines3\ndescription: 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.\nlicense: MIT\ncompatibility: Requires Python 3.10+, PyTorch >= 2.3, and stable-baselines3 2.8+. Gymnasium environments; optional extras for TensorBoard and Atari (ale-py).\nallowed-tools: Read Write Edit Bash\nmetadata:\n  version: '1.3'\n  category: data-science-and-ml\n  maintainer: Kalaris Labs\n  tags: reinforcement learning, PPO, SAC, DQN, Gymnasium\n---\n\n# Stable Baselines3\n\n## Overview\n\nStable 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.\n\n**Current upstream:** SB3 **2.8.0** (April 2026). Docs: [stable-baselines3.readthedocs.io](https:\u002F\u002Fstable-baselines3.readthedocs.io\u002Fen\u002Fmaster\u002F).\n\n## Installation\n\nTested against **stable-baselines3 2.8.0**. Requires **Python 3.10+** (3.9 dropped in 2.8.0) and **PyTorch >= 2.3**.\n\n```bash\n# Basic installation\nuv pip install \"stable-baselines3>=2.8\"\n\n# With extra dependencies (TensorBoard, ale-py for Atari, etc.)\nuv pip install \"stable-baselines3[extra]>=2.8\"\n```\n\nOn zsh, quote brackets: `uv pip install 'stable-baselines3[extra]>=2.8'`.\n\nFor MuJoCo continuous-control benchmarks:\n\n```bash\nuv pip install \"gymnasium[mujoco]\"\n```\n\nCheck your version:\n\n```python\nimport stable_baselines3\nprint(stable_baselines3.__version__)\n```\n\n## Related Projects\n\n- **[SB3-Contrib](https:\u002F\u002Fgithub.com\u002FStable-Baselines-Team\u002Fstable-baselines3-contrib)**: experimental algorithms (MaskablePPO, CrossQ, QR-DQN, RecurrentPPO) — separate `sb3-contrib` package\n- **[RL Baselines3 Zoo](https:\u002F\u002Fgithub.com\u002FDLR-RM\u002Frl-baselines3-zoo)**: pre-trained agents, hyperparameters, training scripts\n- **[SBX](https:\u002F\u002Fgithub.com\u002Faraffin\u002Fsbx)**: SB3 + JAX implementations for users who prefer JAX over PyTorch\n\n## Core Capabilities\n\n### 1. Training RL Agents\n\n**Basic Training Pattern:**\n\n```python\nimport gymnasium as gym\nfrom stable_baselines3 import PPO\n\n# Create environment\nenv = gym.make(\"CartPole-v1\")\n\n# Initialize agent (device=\"cpu\" is often faster for MlpPolicy on small envs)\nmodel = PPO(\"MlpPolicy\", env, verbose=1)\n\n# Train the agent\nmodel.learn(total_timesteps=10000)\n\n# Save the model\nmodel.save(\"ppo_cartpole\")\n\n# Load the model (without prior instantiation)\nmodel = PPO.load(\"ppo_cartpole\", env=env)\n```\n\n**Important Notes:**\n- `total_timesteps` is a lower bound; actual training may exceed this due to batch collection\n- Use `model.load()` as a static method, not on an existing instance\n- The replay buffer is NOT saved with the model to save space\n\n**Algorithm Selection:**\nUse `references\u002Falgorithms.md` for detailed algorithm characteristics and selection guidance. Quick reference:\n- **PPO\u002FA2C**: General-purpose, supports all action space types, good for multiprocessing\n- **SAC\u002FTD3**: Continuous control, off-policy, sample-efficient\n- **DQN**: Discrete actions, off-policy\n- **HER**: Goal-conditioned tasks\n\nSee `scripts\u002Ftrain_rl_agent.py` for a complete training template with best practices.\n\n### 2. Custom Environments\n\n**Requirements:**\nCustom environments must inherit from `gymnasium.Env` and implement:\n- `__init__()`: Define action_space and observation_space\n- `reset(seed, options)`: Return initial observation and info dict\n- `step(action)`: Return observation, reward, terminated, truncated, info\n- `render()`: Visualization (optional)\n- `close()`: Cleanup resources\n\n**Key Constraints:**\n- Image observations must be `np.uint8` in range [0, 255]\n- Use channel-first format when possible (channels, height, width)\n- SB3 normalizes images automatically by dividing by 255\n- Set `normalize_images=False` in policy_kwargs if pre-normalized\n- SB3 does NOT support `Discrete` or `MultiDiscrete` spaces with `start!=0`\n\n**Validation:**\n```python\nfrom stable_baselines3.common.env_checker import check_env\n\ncheck_env(env, warn=True)\n```\n\nSee `scripts\u002Fcustom_env_template.py` for a complete custom environment template and `references\u002Fcustom_environments.md` for comprehensive guidance.\n\n### 3. Vectorized Environments\n\n**Purpose:**\nVectorized environments run multiple environment instances in parallel, accelerating training and enabling certain wrappers (frame-stacking, normalization).\n\n**Types:**\n- **DummyVecEnv**: Sequential execution on current process (for lightweight environments)\n- **SubprocVecEnv**: Parallel execution across processes (for compute-heavy environments)\n\n**Quick Setup:**\n```python\nfrom stable_baselines3.common.env_util import make_vec_env\n\n# Create 4 parallel environments\nenv = make_vec_env(\"CartPole-v1\", n_envs=4, vec_env_cls=SubprocVecEnv)\n\nmodel = PPO(\"MlpPolicy\", env, verbose=1)\nmodel.learn(total_timesteps=25000)\n```\n\n**Off-Policy Optimization:**\nWhen 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.\n\n**API Differences:**\n- `reset()` returns only observations (info available in `vec_env.reset_infos`)\n- `step()` returns 4-tuple: `(obs, rewards, dones, infos)` not 5-tuple\n- Environments auto-reset after episodes\n- Terminal observations available via `infos[env_idx][\"terminal_observation\"]`\n\nSee `references\u002Fvectorized_envs.md` for detailed information on wrappers and advanced usage.\n\n### 4. Callbacks for Monitoring and Control\n\n**Purpose:**\nCallbacks enable monitoring metrics, saving checkpoints, implementing early stopping, and custom training logic without modifying core algorithms.\n\n**Common Callbacks:**\n- **EvalCallback**: Evaluate periodically and save best model\n- **CheckpointCallback**: Save model checkpoints at intervals\n- **StopTrainingOnRewardThreshold**: Stop when target reward reached\n- **ProgressBarCallback**: Display training progress with timing\n\n**Custom Callback Structure:**\n```python\nfrom stable_baselines3.common.callbacks import BaseCallback\n\nclass CustomCallback(BaseCallback):\n    def _on_training_start(self):\n        # Called before first rollout\n        pass\n\n    def _on_step(self):\n        # Called after each environment step\n        # Return False to stop training\n        return True\n\n    def _on_rollout_end(self):\n        # Called at end of rollout\n        pass\n```\n\n**Available Attributes:**\n- `self.model`: The RL algorithm instance\n- `self.num_timesteps`: Total environment steps\n- `self.training_env`: The training environment\n\n**Chaining Callbacks:**\n```python\nfrom stable_baselines3.common.callbacks import CallbackList\n\ncallback = CallbackList([eval_callback, checkpoint_callback, custom_callback])\nmodel.learn(total_timesteps=10000, callback=callback)\n```\n\nSee `references\u002Fcallbacks.md` for comprehensive callback documentation.\n\n### 5. Model Persistence and Inspection\n\n**Saving and Loading:**\n```python\n# Save model\nmodel.save(\"model_name\")\n\n# Save normalization statistics (if using VecNormalize)\nvec_env.save(\"vec_normalize.pkl\")\n\n# Load model\nmodel = PPO.load(\"model_name\", env=env)\n\n# Load normalization statistics\nvec_env = VecNormalize.load(\"vec_normalize.pkl\", vec_env)\n```\n\n**Parameter Access:**\n```python\n# Get parameters\nparams = model.get_parameters()\n\n# Set parameters\nmodel.set_parameters(params)\n\n# Access PyTorch state dict\nstate_dict = model.policy.state_dict()\n```\n\n### 6. Evaluation and Recording\n\n**Evaluation:**\n```python\nfrom stable_baselines3.common.evaluation import evaluate_policy\n\nmean_reward, std_reward = evaluate_policy(\n    model,\n    env,\n    n_eval_episodes=10,\n    deterministic=True\n)\n```\n\n**Video Recording:**\n```python\nfrom stable_baselines3.common.vec_env import VecVideoRecorder\n\n# Wrap environment with video recorder\nenv = VecVideoRecorder(\n    env,\n    \"videos\u002F\",\n    record_video_trigger=lambda x: x % 2000 == 0,\n    video_length=200\n)\n```\n\nSee `scripts\u002Fevaluate_agent.py` for a complete evaluation and recording template.\n\n### 7. Advanced Features\n\n**Learning Rate Schedules:**\n```python\ndef linear_schedule(initial_value):\n    def func(progress_remaining):\n        # progress_remaining goes from 1 to 0\n        return progress_remaining * initial_value\n    return func\n\nmodel = PPO(\"MlpPolicy\", env, learning_rate=linear_schedule(0.001))\n```\n\n**Multi-Input Policies (Dict Observations):**\n```python\nmodel = PPO(\"MultiInputPolicy\", env, verbose=1)\n```\nUse when observations are dictionaries (e.g., combining images with sensor data).\n\n**Hindsight Experience Replay:**\n```python\nfrom stable_baselines3 import SAC, HerReplayBuffer\n\nmodel = SAC(\n    \"MultiInputPolicy\",\n    env,\n    replay_buffer_class=HerReplayBuffer,\n    replay_buffer_kwargs=dict(\n        n_sampled_goal=4,\n        goal_selection_strategy=\"future\",\n    ),\n)\n```\n\n**TensorBoard Integration:**\n```python\nmodel = PPO(\"MlpPolicy\", env, tensorboard_log=\".\u002Ftensorboard\u002F\")\nmodel.learn(total_timesteps=10000)\n```\n\n## Workflow Guidance\n\n**Starting a New RL Project:**\n\n1. **Define the problem**: Identify observation space, action space, and reward structure\n2. **Choose algorithm**: Use `references\u002Falgorithms.md` for selection guidance\n3. **Create\u002Fadapt environment**: Use `scripts\u002Fcustom_env_template.py` if needed\n4. **Validate environment**: Always run `check_env()` before training\n5. **Set up training**: Use `scripts\u002Ftrain_rl_agent.py` as starting template\n6. **Add monitoring**: Implement callbacks for evaluation and checkpointing\n7. **Optimize performance**: Consider vectorized environments for speed\n8. **Evaluate and iterate**: Use `scripts\u002Fevaluate_agent.py` for assessment\n\n**Common Issues:**\n\n- **Memory errors**: Reduce `buffer_size` for off-policy algorithms or use fewer parallel environments\n- **Slow training**: Consider SubprocVecEnv for parallel environments\n- **Unstable training**: Try different algorithms, tune hyperparameters, or check reward scaling\n- **Import errors**: Ensure `stable_baselines3` is installed: `uv pip install 'stable-baselines3[extra]>=2.8'`\n\n## Resources\n\n### scripts\u002F\n- `train_rl_agent.py`: Complete training script template with best practices\n- `evaluate_agent.py`: Agent evaluation and video recording template\n- `custom_env_template.py`: Custom Gym environment template\n\n### references\u002F\n- `algorithms.md`: Detailed algorithm comparison and selection guide\n- `custom_environments.md`: Comprehensive custom environment creation guide\n- `callbacks.md`: Complete callback system reference\n- `vectorized_envs.md`: Vectorized environment usage and wrappers\n\n## Agent operating procedure\n\n1. **Check the environment.** Confirm the Python environment and library versions (`python -c \"import pkg; print(pkg.__version__)\"`) and inspect the data's shape, types and missing values.\n2. **Pin down the inputs.** Confirm formats, identifiers and parameters from the data or the user. Ask rather than guess any value that changes the result.\n3. **Run a small version first.** Run on a sample or a single fold first and check runtime and memory.\n4. **Execute the full task** using the instructions and references above.\n5. **Validate the result.** Use held-out data, fixed random seeds and appropriate metrics; check for leakage; report uncertainty (CIs, std over seeds).\n6. **Report.** State what was run (versions, commands, parameters), what was checked, and what is still uncertain.\n\n| If this happens | Do this |\n|---|---|\n| Out-of-memory or very slow execution | Subsample, use chunked or lazy computation, or reduce model size, and tell the user what changed. |\n| A function, flag or endpoint in these instructions is missing in the installed version | Check the installed version's own documentation (`help()`, `--help`, official docs), adapt, and tell the user. Never invent an API. |\n| A required input, identifier or parameter is ambiguous | Ask the user, or state the assumption explicitly before running. |\n\n**Integrity rules**\n\n- Never fabricate results, parameters, identifiers, citations or statistics. If something cannot be run or verified, say so plainly.\n- Never report a metric you did not compute in this session; show the code path that produced every number.\n- Treat version-specific details here as possibly outdated: confirm them against the official documentation for the installed version.\n- Ask before actions that cost money, consume shared GPUs or cloud quota, touch personal or patient data, or cannot be undone.\n","# Stable Baselines3\n\n## Overview\n\nStable 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.\n\n**Current upstream:** SB3 **2.8.0** (April 2026). Docs: [stable-baselines3.readthedocs.io](https:\u002F\u002Fstable-baselines3.readthedocs.io\u002Fen\u002Fmaster\u002F).\n\n## Installation\n\nTested against **stable-baselines3 2.8.0**. Requires **Python 3.10+** (3.9 dropped in 2.8.0) and **PyTorch >= 2.3**.\n\n```bash\n# Basic installation\nuv pip install \"stable-baselines3>=2.8\"\n\n# With extra dependencies (TensorBoard, ale-py for Atari, etc.)\nuv pip install \"stable-baselines3[extra]>=2.8\"\n```\n\nOn zsh, quote brackets: `uv pip install 'stable-baselines3[extra]>=2.8'`.\n\nFor MuJoCo continuous-control benchmarks:\n\n```bash\nuv pip install \"gymnasium[mujoco]\"\n```\n\nCheck your version:\n\n```python\nimport stable_baselines3\nprint(stable_baselines3.__version__)\n```\n\n## Related Projects\n\n- **[SB3-Contrib](https:\u002F\u002Fgithub.com\u002FStable-Baselines-Team\u002Fstable-baselines3-contrib)**: experimental algorithms (MaskablePPO, CrossQ, QR-DQN, RecurrentPPO) — separate `sb3-contrib` package\n- **[RL Baselines3 Zoo](https:\u002F\u002Fgithub.com\u002FDLR-RM\u002Frl-baselines3-zoo)**: pre-trained agents, hyperparameters, training scripts\n- **[SBX](https:\u002F\u002Fgithub.com\u002Faraffin\u002Fsbx)**: SB3 + JAX implementations for users who prefer JAX over PyTorch\n\n## Core Capabilities\n\n### 1. Training RL Agents\n\n**Basic Training Pattern:**\n\n```python\nimport gymnasium as gym\nfrom stable_baselines3 import PPO\n\n# Create environment\nenv = gym.make(\"CartPole-v1\")\n\n# Initialize agent (device=\"cpu\" is often faster for MlpPolicy on small envs)\nmodel = PPO(\"MlpPolicy\", env, verbose=1)\n\n# Train the agent\nmodel.learn(total_timesteps=10000)\n\n# Save the model\nmodel.save(\"ppo_cartpole\")\n\n# Load the model (without prior instantiation)\nmodel = PPO.load(\"ppo_cartpole\", env=env)\n```\n\n**Important Notes:**\n- `total_timesteps` is a lower bound; actual training may exceed this due to batch collection\n- Use `model.load()` as a static method, not on an existing instance\n- The replay buffer is NOT saved with the model to save space\n\n**Algorithm Selection:**\nUse `references\u002Falgorithms.md` for detailed algorithm characteristics and selection guidance. Quick reference:\n- **PPO\u002FA2C**: General-purpose, supports all action space types, good for multiprocessing\n- **SAC\u002FTD3**: Continuous control, off-policy, sample-efficient\n- **DQN**: Discrete actions, off-policy\n- **HER**: Goal-conditioned tasks\n\nSee `scripts\u002Ftrain_rl_agent.py` for a complete training template with best practices.\n\n### 2. Custom Environments\n\n**Requirements:**\nCustom environments must inherit from `gymnasium.Env` and implement:\n- `__init__()`: Define action_space and observation_space\n- `reset(seed, options)`: Return initial observation and info dict\n- `step(action)`: Return observation, reward, terminated, truncated, info\n- `render()`: Visualization (optional)\n- `close()`: Cleanup resources\n\n**Key Constraints:**\n- Image observations must be `np.uint8` in range [0, 255]\n- Use channel-first format when possible (channels, height, width)\n- SB3 normalizes images automatically by dividing by 255\n- Set `normalize_images=False` in policy_kwargs if pre-normalized\n- SB3 does NOT support `Discrete` or `MultiDiscrete` spaces with `start!=0`\n\n**Validation:**\n```python\nfrom stable_baselines3.common.env_checker import check_env\n\ncheck_env(env, warn=True)\n```\n\nSee `scripts\u002Fcustom_env_template.py` for a complete custom environment template and `references\u002Fcustom_environments.md` for comprehensive guidance.\n\n### 3. Vectorized Environments\n\n**Purpose:**\nVectorized environments run multiple environment instances in parallel, accelerating training and enabling certain wrappers (frame-stacking, normalization).\n\n**Types:**\n- **DummyVecEnv**: Sequential execution on current process (for lightweight environments)\n- **SubprocVecEnv**: Parallel execution across processes (for compute-heavy environments)\n\n**Quick Setup:**\n```python\nfrom stable_baselines3.common.env_util import make_vec_env\n\n# Create 4 parallel environments\nenv = make_vec_env(\"CartPole-v1\", n_envs=4, vec_env_cls=SubprocVecEnv)\n\nmodel = PPO(\"MlpPolicy\", env, verbose=1)\nmodel.learn(total_timesteps=25000)\n```\n\n**Off-Policy Optimization:**\nWhen 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.\n\n**API Differences:**\n- `reset()` returns only observations (info available in `vec_env.reset_infos`)\n- `step()` returns 4-tuple: `(obs, rewards, dones, infos)` not 5-tuple\n- Environments auto-reset after episodes\n- Terminal observations available via `infos[env_idx][\"terminal_observation\"]`\n\nSee `references\u002Fvectorized_envs.md` for detailed information on wrappers and advanced usage.\n\n### 4. Callbacks for Monitoring and Control\n\n**Purpose:**\nCallbacks enable monitoring metrics, saving checkpoints, implementing early stopping, and custom training logic without modifying core algorithms.\n\n**Common Callbacks:**\n- **EvalCallback**: Evaluate periodically and save best model\n- **CheckpointCallback**: Save model checkpoints at intervals\n- **StopTrainingOnRewardThreshold**: Stop when target reward reached\n- **ProgressBarCallback**: Display training progress with timing\n\n**Custom Callback Structure:**\n```python\nfrom stable_baselines3.common.callbacks import BaseCallback\n\nclass CustomCallback(BaseCallback):\n    def _on_training_start(self):\n        # Called before first rollout\n        pass\n\n    def _on_step(self):\n        # Called after each environment step\n        # Return False to stop training\n        return True\n\n    def _on_rollout_end(self):\n        # Called at end of rollout\n        pass\n```\n\n**Available Attributes:**\n- `self.model`: The RL algorithm instance\n- `self.num_timesteps`: Total environment steps\n- `self.training_env`: The training environment\n\n**Chaining Callbacks:**\n```python\nfrom stable_baselines3.common.callbacks import CallbackList\n\ncallback = CallbackList([eval_callback, checkpoint_callback, custom_callback])\nmodel.learn(total_timesteps=10000, callback=callback)\n```\n\nSee `references\u002Fcallbacks.md` for comprehensive callback documentation.\n\n### 5. Model Persistence and Inspection\n\n**Saving and Loading:**\n```python\n# Save model\nmodel.save(\"model_name\")\n\n# Save normalization statistics (if using VecNormalize)\nvec_env.save(\"vec_normalize.pkl\")\n\n# Load model\nmodel = PPO.load(\"model_name\", env=env)\n\n# Load normalization statistics\nvec_env = VecNormalize.load(\"vec_normalize.pkl\", vec_env)\n```\n\n**Parameter Access:**\n```python\n# Get parameters\nparams = model.get_parameters()\n\n# Set parameters\nmodel.set_parameters(params)\n\n# Access PyTorch state dict\nstate_dict = model.policy.state_dict()\n```\n\n### 6. Evaluation and Recording\n\n**Evaluation:**\n```python\nfrom stable_baselines3.common.evaluation import evaluate_policy\n\nmean_reward, std_reward = evaluate_policy(\n    model,\n    env,\n    n_eval_episodes=10,\n    deterministic=True\n)\n```\n\n**Video Recording:**\n```python\nfrom stable_baselines3.common.vec_env import VecVideoRecorder\n\n# Wrap environment with video recorder\nenv = VecVideoRecorder(\n    env,\n    \"videos\u002F\",\n    record_video_trigger=lambda x: x % 2000 == 0,\n    video_length=200\n)\n```\n\nSee `scripts\u002Fevaluate_agent.py` for a complete evaluation and recording template.\n\n### 7. Advanced Features\n\n**Learning Rate Schedules:**\n```python\ndef linear_schedule(initial_value):\n    def func(progress_remaining):\n        # progress_remaining goes from 1 to 0\n        return progress_remaining * initial_value\n    return func\n\nmodel = PPO(\"MlpPolicy\", env, learning_rate=linear_schedule(0.001))\n```\n\n**Multi-Input Policies (Dict Observations):**\n```python\nmodel = PPO(\"MultiInputPolicy\", env, verbose=1)\n```\nUse when observations are dictionaries (e.g., combining images with sensor data).\n\n**Hindsight Experience Replay:**\n```python\nfrom stable_baselines3 import SAC, HerReplayBuffer\n\nmodel = SAC(\n    \"MultiInputPolicy\",\n    env,\n    replay_buffer_class=HerReplayBuffer,\n    replay_buffer_kwargs=dict(\n        n_sampled_goal=4,\n        goal_selection_strategy=\"future\",\n    ),\n)\n```\n\n**TensorBoard Integration:**\n```python\nmodel = PPO(\"MlpPolicy\", env, tensorboard_log=\".\u002Ftensorboard\u002F\")\nmodel.learn(total_timesteps=10000)\n```\n\n## Workflow Guidance\n\n**Starting a New RL Project:**\n\n1. **Define the problem**: Identify observation space, action space, and reward structure\n2. **Choose algorithm**: Use `references\u002Falgorithms.md` for selection guidance\n3. **Create\u002Fadapt environment**: Use `scripts\u002Fcustom_env_template.py` if needed\n4. **Validate environment**: Always run `check_env()` before training\n5. **Set up training**: Use `scripts\u002Ftrain_rl_agent.py` as starting template\n6. **Add monitoring**: Implement callbacks for evaluation and checkpointing\n7. **Optimize performance**: Consider vectorized environments for speed\n8. **Evaluate and iterate**: Use `scripts\u002Fevaluate_agent.py` for assessment\n\n**Common Issues:**\n\n- **Memory errors**: Reduce `buffer_size` for off-policy algorithms or use fewer parallel environments\n- **Slow training**: Consider SubprocVecEnv for parallel environments\n- **Unstable training**: Try different algorithms, tune hyperparameters, or check reward scaling\n- **Import errors**: Ensure `stable_baselines3` is installed: `uv pip install 'stable-baselines3[extra]>=2.8'`\n\n## Resources\n\n### scripts\u002F\n- `train_rl_agent.py`: Complete training script template with best practices\n- `evaluate_agent.py`: Agent evaluation and video recording template\n- `custom_env_template.py`: Custom Gym environment template\n\n### references\u002F\n- `algorithms.md`: Detailed algorithm comparison and selection guide\n- `custom_environments.md`: Comprehensive custom environment creation guide\n- `callbacks.md`: Complete callback system reference\n- `vectorized_envs.md`: Vectorized environment usage and wrappers\n\n## Agent operating procedure\n\n1. **Check the environment.** Confirm the Python environment and library versions (`python -c \"import pkg; print(pkg.__version__)\"`) and inspect the data's shape, types and missing values.\n2. **Pin down the inputs.** Confirm formats, identifiers and parameters from the data or the user. Ask rather than guess any value that changes the result.\n3. **Run a small version first.** Run on a sample or a single fold first and check runtime and memory.\n4. **Execute the full task** using the instructions and references above.\n5. **Validate the result.** Use held-out data, fixed random seeds and appropriate metrics; check for leakage; report uncertainty (CIs, std over seeds).\n6. **Report.** State what was run (versions, commands, parameters), what was checked, and what is still uncertain.\n\n| If this happens | Do this |\n|---|---|\n| Out-of-memory or very slow execution | Subsample, use chunked or lazy computation, or reduce model size, and tell the user what changed. |\n| A function, flag or endpoint in these instructions is missing in the installed version | Check the installed version's own documentation (`help()`, `--help`, official docs), adapt, and tell the user. Never invent an API. |\n| A required input, identifier or parameter is ambiguous | Ask the user, or state the assumption explicitly before running. |\n\n**Integrity rules**\n\n- Never fabricate results, parameters, identifiers, citations or statistics. If something cannot be run or verified, say so plainly.\n- Never report a metric you did not compute in this session; show the code path that produced every number.\n- Treat version-specific details here as possibly outdated: confirm them against the official documentation for the installed version.\n- Ask before actions that cost money, consume shared GPUs or cloud quota, touch personal or patient data, or cannot be undone.\n",{"name":5,"license":15,"metadata":49,"description":7,"allowed-tools":54,"compatibility":55},{"tags":50,"version":51,"category":52,"maintainer":53},"reinforcement learning, PPO, SAC, DQN, Gymnasium","1.3","data-science-and-ml","Kalaris Labs","Read Write Edit Bash","Requires Python 3.10+, PyTorch >= 2.3, and stable-baselines3 2.8+. Gymnasium environments; optional extras for TensorBoard and Atari (ale-py).","main","0da4485785ee599388900be50db1635489d53056",".agents\u002Fskills\u002Fkal-stable-baselines3","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6","https:\u002F\u002Fdisha6.6.thenitishkr.in\u002F","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh","www.thenitishkr","thenitishkr | AI • Cyber-security • Research\r\n","2026-11-08 03:33:25",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add Tashima-Tarsh\u002FDisha6.6 --skill stable-baselines3",{"tool":71,"command":72},"bunx","bunx skills add Tashima-Tarsh\u002FDisha6.6 --skill stable-baselines3",{"tool":74,"command":75},"pnpm","pnpm dlx skills add Tashima-Tarsh\u002FDisha6.6 --skill stable-baselines3","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-stable-baselines3\u002FSKILL.md",true,[79,85,89,93,97,103,107],{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Falgorithms.md","REFERENCE","参考文档",10953,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-stable-baselines3\u002Freferences\u002Falgorithms.md",{"path":86,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fcallbacks.md",16377,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-stable-baselines3\u002Freferences\u002Fcallbacks.md",{"path":90,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Fcustom_environments.md",14124,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-stable-baselines3\u002Freferences\u002Fcustom_environments.md",{"path":94,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Fvectorized_envs.md",15453,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-stable-baselines3\u002Freferences\u002Fvectorized_envs.md",{"path":98,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":101,"sourceHtmlUrl":102},"scripts\u002Fcustom_env_template.py","SCRIPT","脚本",9350,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-stable-baselines3\u002Fscripts\u002Fcustom_env_template.py",{"path":104,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":105,"sourceHtmlUrl":106},"scripts\u002Fevaluate_agent.py",7335,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-stable-baselines3\u002Fscripts\u002Fevaluate_agent.py",{"path":108,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":109,"sourceHtmlUrl":110},"scripts\u002Ftrain_rl_agent.py",5123,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-stable-baselines3\u002Fscripts\u002Ftrain_rl_agent.py",[112,141,165,190,215,239],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":121,"publishedAt":44},"01M6QRD07D4TGNDK6VJ4EHF8BV","youtube-full","Use when the user needs YouTube transcripts, video search, channel browsing, playlist extraction, or content monitoring. Trigger phrases: 'get the transcript for', 'search YouTube for', 'what are the latest videos on', 'list this playlist', 'monitor this channel', or any request involving a YouTube URL, video ID, or @handle. Do NOT use for downloading video or audio files, YouTube engagement data (likes, comments), or private\u002Fage-restricted videos.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fyoutube-full\u002FSKILL.md",[118],{"categoryNo":119,"categoryName":120,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[122,123,124,125,126,127,38,128,129,130,131,132,133,134,135,136,137,138,139,140],"youtube full","youtube","full","transcript","search","monitoring","Video","Audio","list","files","do","get","age","trigger","URL","for","browsing","request","youtube transcripts",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":44},"01M6QRCJ3112VYPA97YG7KGMC2","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fx-twitter-growth\u002FSKILL.md",[],[148,149,150,151,126,152,153,154,155,156,157,158,34,159,160,161,162,163,164,137],"twitter","x twitter growth","growth","research","content","engineering","plan","web search","competitors","analyze","engine","strategy","use","platform","grow","posting","competitive",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":172,"publishedAt":44},"01M6QRBN3EHQNJY42RERP7A149","write-a-skill","Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrite-a-skill\u002FSKILL.md",[171],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[173,34,174,175,176,177,178,179,160,180,181,56,182,183,184,185,186,187,188,189],"write a skill","github","create","https","productivity","matt pocock","direct","example","build","new skill","structure","new agent","resources","with","tree","progressive disclosure","author",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":196,"publishedAt":44},"01M6QRB6G8P33PNGAF9Y69EJ9T","wrap-up","Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says \"wrap up\", \"close this out\", \"what do I own now\", \"give me the summary\", \"recap the agent\", or when the orchestrator routes phase=wrap-up. primitives_inventory.py tables everything owned (agent, environment, session, memory, outcome, deployment); overview_page.py regenerates a self-contained .\u002Fmy-agent\u002Fagent-overview.html; upgrade_suggester.py ranks the next moves from recorded deferrals plus standing hardening steps. Companion to run-without-you; the last stop before phase=done.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrap-up\u002FSKILL.md",[],[197,198,199,200,201,202,203,204,205,160,206,132,207,208,209,210,211,212,213,214],"wrap up","up","wrap","gemini","deployment","run","file","hardening","closeout","stop","upgrade","founder","close","companion","you","tables","directions","phase",{"skillNo":216,"name":217,"nameZh":6,"description":218,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":219,"categories":220,"keywords":222,"publishedAt":44},"01M6QRA5AYC1RBFZ39GTWGS3N8","workflow-builder","Design and write deterministic multi-agent workflow scripts (.js files in .claude\u002Fworkflows\u002F) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fworkflow-builder\u002FSKILL.md",[221],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[223,224,225,226,227,175,202,228,229,230,231,232,34,233,131,234,235,236,237,238],"workflow","workflow builder","builder","design","workflows","code","orchestrate","pipeline","loop","multi-agent","context","across","fresh","scripts","judge","claude code workflow",{"skillNo":240,"name":241,"nameZh":6,"description":242,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":243,"categories":244,"keywords":245,"publishedAt":44},"01M6QR7QMCZESKQA0ERW1E657M","weekly-review","Use when someone wants to run a weekly review, close open loops, audit stalled projects and commitments, get their system back to trusted, restart a lapsed review habit, or says \"\u002Fcs:weekly-review\". Walks David Allen's three-phase loop — GET CLEAR, GET CURRENT, GET CREATIVE — with deterministic scripts that inventory open loops, gate the checklist with named gaps, and score commitment health 0-100.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweekly-review\u002FSKILL.md",[],[246,247,248,249,250,251,252,253,254,231,255,256,257,258,259,260,133,261,262,214],"review","weekly review","weekly","deterministic scripts","reflect","feeds","inventory","open","team","projects","project-management","scanner","conversation","back","project","sprint","cadence"]