[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M794AMWD3JN46M6TH3WRKE5K":3,"skill-same:01M794AMWD3JN46M6TH3WRKE5K":66},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M794AMWD3JN46M6TH3WRKE5K","tuning-optimization",null,"Build and validate Optuna hyperparameter optimization commands, study reuse, and report artifacts for RL Zoo.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frl-baselines3-zoo\u002Fsub-skills\u002Ftuning-optimization\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: tuning-optimization\ndescription: \"Build and validate Optuna hyperparameter optimization commands,\n  study reuse, and report artifacts for RL Zoo.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# tuning-optimization\n\nUse this sub-skill when a task is specifically about RL Zoo Optuna hyperparameter optimization (HPO): starting `-optimize` \u002F `--optimize-hyperparameters`, choosing sampler\u002Fpruner\u002Fbudget flags, coordinating shared studies, loading a stored trial, or interpreting HPO report artifacts.\n\n## Route first\n\n- Base training flags, run budgets, device\u002Fthread\u002Fvector-env choices, resume\u002Fcheckpoint flags, and ordinary training lifecycle: [`..\u002Ftraining-cli\u002FSKILL.md`](..\u002Ftraining-cli\u002FSKILL.md).\n- YAML\u002FPython hyperparameter files, `-params` override grammar, wrappers\u002Fcallbacks, and config syntax: [`..\u002Fconfig-hyperparams\u002FSKILL.md`](..\u002Fconfig-hyperparams\u002FSKILL.md).\n- Plotting or benchmarking the resulting files: [`..\u002Fplotting-benchmarking\u002FSKILL.md`](..\u002Fplotting-benchmarking\u002FSKILL.md).\n- Optional dependency and console-entry caveats: [`..\u002F..\u002Freferences\u002Finstall-and-environment.md`](..\u002F..\u002Freferences\u002Finstall-and-environment.md).\n\n## Runtime entry points\n\nPrefer installed-package commands:\n\n- `python -m rl_zoo3.train ... --optimize-hyperparameters` is the safest base command for HPO because it targets the train module directly.\n- `rl_zoo3 train ... --optimize-hyperparameters` is equivalent when the console entry point and optional plot-import path are available.\n\nUse the bundled non-executing helper to build and validate command strings:\n\n```bash\npython scripts\u002Ftuning_command_builder.py --help\n```\n\nThe helper does not start training or optimization. It validates high-risk HPO combinations such as `--pruner halving` with too few jobs, `--sampler auto` without `optunahub`, unsupported HPO algorithms, and `--trial-id` without a reusable study.\n\n## References\n\n- [`references\u002Foptuna-tuning.md`](references\u002Foptuna-tuning.md) — HPO command patterns, flag semantics, lifecycle, and search-space notes.\n- [`references\u002Foptuna-study-artifacts.md`](references\u002Foptuna-study-artifacts.md) — report files, per-trial evaluation logs, storage reuse, and deprecated study-parser handling.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) — common HPO failures and fast fixes.\n\n## Operating boundaries\n\n- HPO is distinct from ordinary training: always make the training timestep budget and Optuna trial budget explicit before proposing a real run.\n- Treat search spaces as algorithm-specific; if an algorithm is not in the HPO sampler\u002Fconverter map, do not claim it is tunable through RL Zoo HPO without extending that map.\n- Do not copy or rely on deprecated source helper scripts for new workflows. Use storage plus `--study-name` \u002F `--trial-id` for trial reuse.\n","# tuning-optimization\n\nUse this sub-skill when a task is specifically about RL Zoo Optuna hyperparameter optimization (HPO): starting `-optimize` \u002F `--optimize-hyperparameters`, choosing sampler\u002Fpruner\u002Fbudget flags, coordinating shared studies, loading a stored trial, or interpreting HPO report artifacts.\n\n## Route first\n\n- Base training flags, run budgets, device\u002Fthread\u002Fvector-env choices, resume\u002Fcheckpoint flags, and ordinary training lifecycle: [`..\u002Ftraining-cli\u002FSKILL.md`](..\u002Ftraining-cli\u002FSKILL.md).\n- YAML\u002FPython hyperparameter files, `-params` override grammar, wrappers\u002Fcallbacks, and config syntax: [`..\u002Fconfig-hyperparams\u002FSKILL.md`](..\u002Fconfig-hyperparams\u002FSKILL.md).\n- Plotting or benchmarking the resulting files: [`..\u002Fplotting-benchmarking\u002FSKILL.md`](..\u002Fplotting-benchmarking\u002FSKILL.md).\n- Optional dependency and console-entry caveats: [`..\u002F..\u002Freferences\u002Finstall-and-environment.md`](..\u002F..\u002Freferences\u002Finstall-and-environment.md).\n\n## Runtime entry points\n\nPrefer installed-package commands:\n\n- `python -m rl_zoo3.train ... --optimize-hyperparameters` is the safest base command for HPO because it targets the train module directly.\n- `rl_zoo3 train ... --optimize-hyperparameters` is equivalent when the console entry point and optional plot-import path are available.\n\nUse the bundled non-executing helper to build and validate command strings:\n\n```bash\npython scripts\u002Ftuning_command_builder.py --help\n```\n\nThe helper does not start training or optimization. It validates high-risk HPO combinations such as `--pruner halving` with too few jobs, `--sampler auto` without `optunahub`, unsupported HPO algorithms, and `--trial-id` without a reusable study.\n\n## References\n\n- [`references\u002Foptuna-tuning.md`](references\u002Foptuna-tuning.md) — HPO command patterns, flag semantics, lifecycle, and search-space notes.\n- [`references\u002Foptuna-study-artifacts.md`](references\u002Foptuna-study-artifacts.md) — report files, per-trial evaluation logs, storage reuse, and deprecated study-parser handling.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) — common HPO failures and fast fixes.\n\n## Operating boundaries\n\n- HPO is distinct from ordinary training: always make the training timestep budget and Optuna trial budget explicit before proposing a real run.\n- Treat search spaces as algorithm-specific; if an algorithm is not in the HPO sampler\u002Fconverter map, do not claim it is tunable through RL Zoo HPO without extending that map.\n- Do not copy or rely on deprecated source helper scripts for new workflows. Use storage plus `--study-name` \u002F `--trial-id` for trial reuse.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Frl-baselines3-zoo\u002Fsub-skills\u002Ftuning-optimization",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill tuning-optimization",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill tuning-optimization",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill tuning-optimization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frl-baselines3-zoo\u002Fsub-skills\u002Ftuning-optimization\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Foptuna-study-artifacts.md","REFERENCE","参考文档",3475,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frl-baselines3-zoo\u002Fsub-skills\u002Ftuning-optimization\u002Freferences\u002Foptuna-study-artifacts.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Foptuna-tuning.md",6987,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frl-baselines3-zoo\u002Fsub-skills\u002Ftuning-optimization\u002Freferences\u002Foptuna-tuning.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",4289,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frl-baselines3-zoo\u002Fsub-skills\u002Ftuning-optimization\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Ftuning_command_builder.py","SCRIPT","脚本",11257,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frl-baselines3-zoo\u002Fsub-skills\u002Ftuning-optimization\u002Fscripts\u002Ftuning_command_builder.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]