{"slug":"foryourhealth111-pixel-stable-baselines3","source_name":"foryourhealth111-pixel/stable-baselines3","name":"Foryourhealth111 Pixel/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":8.7,"pass_rate_pct":100,"total_cases":23,"passed_cases":23,"tokens_delta_pct":86.1,"turns_delta_pct":0,"verdict":"pass","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-13T05:59:05.231592+00:00"},"skill_score":1,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":8.7,"with_pass_pct":100,"without_pass_pct":91.3,"tokens_delta_pct":86.1,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":23,"verdict":"pass","never_hurt":true,"completed_at":"2026-08-13T05:59:05.231592+00:00","run_id":"80d3771c-d1f4-4803-a3d1-297d4ee570a2","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":"63e9687c0b236d599d26ff3dbb30b43d2df33d4064d30de636211a299ee9a040","raw_url":"https://app.decimal.ai/s/foryourhealth111-pixel-stable-baselines3/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/foryourhealth111-pixel-stable-baselines3"}