{"slug":"k-dense-ai-stable-baselines3","source_name":"k-dense-ai/stable-baselines3","name":"K Dense AI/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.","version":1,"lift":{"pass_rate_delta_pts":13.64,"pass_rate_pct":100,"total_cases":22,"passed_cases":22,"tokens_delta_pct":110,"turns_delta_pct":0,"verdict":"pass","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-09T10:44:00.409923+00:00"},"skill_score":1,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":13.64,"with_pass_pct":100,"without_pass_pct":86.4,"tokens_delta_pct":110,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"pass","never_hurt":true,"completed_at":"2026-08-09T10:44:00.409923+00:00","run_id":"bc507e21-2b6b-425e-891a-10270868938b","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"MIT license","install_count":0,"manifest_hash":"e43f1870f05c4414d7ab4d2cae7cbdde12c1fc3f5525e18e2d22cd0c7e9d68b3","raw_url":"https://app.decimal.ai/s/k-dense-ai-stable-baselines3/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/k-dense-ai-stable-baselines3"}