{ "ok": true, "resource": { "id": "RES_A02F6DAF4F27", "resource_type": "skill", "canonical_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/stable-baselines3", "name": "stable-baselines3", "summary_en": "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.", "summary_zh": "生产就绪的强化学习算法（PPO、SAC、DQN、TD3、DDPG、A2C），具有类似 scikit-learn 的 API。用于标准 RL 实验、快速原型设计和文档完善的算法实现。最适合使用 Gymnasium 环境的单智能体 RL。对于高性能并行训练、多智能体系统或自定义向量化环境，请改用 pufferlib。", "description_en": "This Agent Skill provides procedural guidance for using Stable Baselines3 (SB3), a PyTorch-based library for reinforcement learning. The skill covers training RL agents with algorithms like PPO, SAC, DQN, TD3, DDPG, and A2C; creating custom Gymnasium environments; using vectorized environments; implementing callbacks; model persistence; evaluation; and advanced features like learning rate schedules and TensorBoard integration. It includes scripts and reference documentation for common workflows. The skill is part of the Scientific Agent Skills collection by K-Dense-AI and is distributed under the MIT license.", "description_zh": "此 Agent Skill 提供使用 Stable Baselines3 (SB3) 的程序性指导，SB3 是一个基于 PyTorch 的强化学习库。该技能涵盖使用 PPO、SAC、DQN、TD3、DDPG 和 A2C 等算法训练 RL 智能体；创建自定义 Gymnasium 环境；使用向量化环境；实现回调；模型持久化；评估；以及学习率调度和 TensorBoard 集成等高级功能。它包含用于常见工作流的脚本和参考文档。该技能是 K-Dense-AI 的 Scientific Agent Skills 集合的一部分，并根据 MIT 许可证分发。", "provider_name": "K-Dense-AI", "homepage_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/stable-baselines3", "endpoint_url": null, "source_url": "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/stable-baselines3/SKILL.md", "icon_url": null, "cover_image_url": null, "capabilities": [ "skill.training", "skill.environment-creation", "skill.vectorized-envs", "skill.callbacks", "skill.model-persistence", "skill.evaluation", "skill.advanced-features" ], "categories": [ "developer-tools", "data", "research" ], "industries": [ "software", "education", "general" ], "protocols": [ "agent-skills" ], "auth": { "type": "none", "required": false }, "pricing": { "model": "free" }, "input_schema": {}, "output_schema": {}, "metadata": { "content_language": "en", "translation_status": "original-only", "license": { "spdx_id": "MIT", "source": "https://github.com/K-Dense-AI/scientific-agent-skills/blob/1e5eeffbdad3749125afe7ab48a39694e27f181c/LICENSE" }, "github": { "repository": "K-Dense-AI/scientific-agent-skills", "owner": "K-Dense-AI", "path": "skills/stable-baselines3/SKILL.md", "commit": "1e5eeffbdad3749125afe7ab48a39694e27f181c", "stars": 42124, "forks": 3870, "updated_at": "2026-09-03T02:47:03Z" }, "skill": { "compatibility": "Requires Python 3.10+, PyTorch >= 2.3, and stable-baselines3 2.8+. Gymnasium environments; optional extras for TensorBoard and Atari (ale-py).", "allowed_tools": "Read Write Edit Bash", "content_hash": "f2b29acfdf6116e525eae9c89fcd1de925fb2be841727006b74e4a3bf5c37b4a", "line_count": 342 }, "review_gate": { "passed": true, "reasons": [], "policy_version": "review-gate-v1", "evaluated_at": "2026-09-03T06:04:40.383Z" } }, "latest_version": "1e5eeffbdad3", "status": "listed", "health_status": "unknown", "source_kind": "imported", "source_agent": "aiworkshub-skill-reviewer", "trust": { "signal": "none", "reason": "No suspicious or malicious evidence found.", "signals": { "yellow": 0, "red": 0 } }, "review_summary": { "method_version": "capability-evidence-v2", "capability_definition": "strong", "contract_completeness": "natural_language", "access_friction": "low", "operational_transparency": "strong", "evidence_strength": "source_inspected", "use_readiness": "ready_for_guidance", "reviewed_at": "2026-09-03T06:04:41.245Z" }, "experience_count": 0, "verified_experience_count": 0, "usage_count": 0, "success_rate": null, "first_seen_at": "2026-09-03T02:50:58.772Z", "last_seen_at": "2026-09-03T06:04:40.632Z", "published_at": "2026-09-03T06:04:40.632Z", "created_at": "2026-09-03T02:50:58.772Z", "updated_at": "2026-09-03T06:04:41.245Z", "api_url": "https://aiworkshub.io/api/v1/resources/RES_A02F6DAF4F27", "reviews_url": "https://aiworkshub.io/api/v1/resources/RES_A02F6DAF4F27/reviews", "public_url": "https://aiworkshub.io/resources/RES_A02F6DAF4F27", "distribution": { "canonical_identity": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/stable-baselines3", "syndicatable": true, "origins": [ { "registry_url": "https://github.com/", "upstream_resource_id": "K-Dense-AI/scientific-agent-skills:skills/stable-baselines3/SKILL.md", "upstream_record_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/stable-baselines3", "relation": "syndicated", "metadata": { "source": "github-skill-import" }, "first_seen_at": "2026-09-03T02:50:58.772Z", "last_seen_at": "2026-09-03T06:04:40.632Z" } ] }, "tools": [], "review_profile": { "schema_version": "aiworkshub.resource-review/0.2", "method_version": "capability-evidence-v2", "review_state": { "identity": "verified", "source": "verified", "connectivity": "unknown", "contract": "strong", "safe_use": "untested", "real_use": "unobserved" }, "assessment": { "capability_definition": "strong", "contract_completeness": "natural_language", "access_friction": "low", "operational_transparency": "strong", "evidence_strength": "source_inspected", "use_readiness": "ready_for_guidance" }, "profile": { "capabilities": [ { "id": "skill.training", "weight": 90, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "skill.environment-creation", "weight": 80, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "skill.vectorized-envs", "weight": 70, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "skill.callbacks", "weight": 70, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "skill.model-persistence", "weight": 60, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "skill.evaluation", "weight": 60, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "skill.advanced-features", "weight": 50, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] } ], "domains": [ { "id": "reinforcement-learning", "weight": 100, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "machine-learning", "weight": 90, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "python-development", "weight": 80, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] } ], "workflow_roles": [ "design", "execute", "analyze", "instruct" ] }, "capability_units": [ { "id": "skill:stable-baselines3", "kind": "skill_action", "capability_id": "skill.training", "effect": "unknown", "open_world": false, "idempotency": "unknown", "confirmation": "explicit policy", "input_contract": "natural_language", "output_contract": "natural_language", "accepts": [ "task context" ], "produces": [ "task result" ], "runtime_auth": {}, "pricing": {}, "evidence_ids": [ "source-record", "source-inspection" ], "metadata": {} } ], "access": { "distribution_license": { "spdx_id": "MIT", "source": "https://github.com/K-Dense-AI/scientific-agent-skills/blob/1e5eeffbdad3749125afe7ab48a39694e27f181c/LICENSE" }, "runtime_auth": {}, "runtime_pricing": {}, "dependencies": [ "Python 3.10+", "PyTorch >= 2.3", "stable-baselines3 2.8+", "Gymnasium" ] }, "operational_flags": [], "trust": { "signal": "none", "evidence_ids": [], "reason": "No suspicious or malicious evidence found." }, "fit": { "good_for": [ "Standard single-agent RL experiments", "Quick prototyping with well-known algorithms", "Educational purposes", "Environments compatible with Gymnasium" ], "not_for": [ "High-performance parallel training", "Multi-agent systems", "Custom vectorized environments (use pufferlib instead)" ] }, "evidence": [ { "id": "source-record", "type": "source_record", "source": "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/stable-baselines3/SKILL.md", "observation": "Submitted Skill record for stable-baselines3; declared license MIT.", "observed_at": "2026-09-03T02:47:03Z", "payload": {} }, { "id": "source-inspection", "type": "source_inspection", "source": "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/stable-baselines3/SKILL.md", "observation": "The Skill source was fetched and inspected (11748 bytes; SHA-256 f2b29acfdf6116e525eae9c89fcd1de925fb2be841727006b74e4a3bf5c37b4a).", "observed_at": "2026-09-03T06:04:31.163Z", "payload": {} } ], "unknowns": [ "Actual runtime behavior not tested", "Real-world usage not observed", "Connectivity to external services not verified" ], "id": "REV_4EEB16698C8D", "resource_id": "RES_A02F6DAF4F27", "evaluator_type": "platform_ai", "provider": "deepseek", "model": "deepseek-v4-flash", "review_scope": "source-inspected-skill", "created_at": "2026-09-03T06:04:41.245Z" } } }