[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7953N581Y2Q77X6MP7S2AXP":3,"skill-same:01M7953N581Y2Q77X6MP7S2AXP":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},"01M7953N581Y2Q77X6MP7S2AXP","torch-agent-training",null,"Route and compose public single-agent PyTorch agents, models, memories, resources, trainers, and experiment controls in skrl 2.1.0.","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\u002Fskrl\u002Fsub-skills\u002Ftorch-agent-training\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: torch-agent-training\ndescription: \"Route and compose public single-agent PyTorch agents, models,\n  memories, resources, trainers, and experiment controls in skrl 2.1.0.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Torch agent training\n\nUse this route for a **single-agent PyTorch** skrl 2.1.0 workflow: choose an\nalgorithm, build its model-role dictionary, allocate rollout\u002Freplay memory,\nconfigure preprocessors\u002Fnoises\u002Fschedulers, select a trainer, and make a safe\ntrain\u002Fevaluate\u002Fresume plan. Start with the bounded component check in\n[`scripts\u002Ftorch_ppo_components.py`](scripts\u002Ftorch_ppo_components.py), then use\nthe references for the exact role keys and construction details.\n\n## Route quickly\n\n1. Establish the observation, optional state, and action spaces through the\n   environment route; this skill does not choose or implement Gymnasium\n   wrappers. See [`..\u002F..\u002Freferences\u002Fframework-selection.md`](..\u002F..\u002Freferences\u002Fframework-selection.md)\n   and [`..\u002F..\u002Freferences\u002Ftroubleshooting.md`](..\u002F..\u002Freferences\u002Ftroubleshooting.md)\n   in the root skill before committing to a backend or trainer.\n2. Choose an algorithm and its required model roles in\n   [`references\u002Falgorithm-and-component-selection.md`](references\u002Falgorithm-and-component-selection.md).\n   Match the policy distribution to the action space and use a deterministic\n   value\u002Fcritic model where the table requires it.\n3. Compose the models, `RandomMemory` (when required), configuration, and agent\n   using [`references\u002Fworkflow-and-api.md`](references\u002Fworkflow-and-api.md).\n   Keep `memory_size` and the agent's rollout\u002Fupdate settings consistent.\n4. Use `SequentialTrainer` for the normal loop, `StepTrainer` when the caller\n   owns each iteration, and `ParallelTrainer` only after checking its process,\n   pickling, shared-memory, and hardware constraints.\n5. Disable writes during a smoke\u002Fevaluation probe, load a checkpoint into an\n   architecture-equivalent agent, and only then enable training or logging.\n   Check workflow-specific failure modes in\n   [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md).\n\n## Boundaries\n\n- **Environment wrappers and space conversion:** route to the\n  [`environment-integration`](..\u002F..\u002Fsub-skills\u002Fenvironment-integration\u002FSKILL.md)\n  sibling.\n- **IPPO\u002FMAPPO, multi-agent trainers, and Runner\u002FYAML:** route to\n  [`..\u002F..\u002Fsub-skills\u002Fmulti-agent-and-runner\u002FSKILL.md`](..\u002F..\u002Fsub-skills\u002Fmulti-agent-and-runner\u002FSKILL.md).\n- **JAX and Warp:** not covered here.\n- Framework-wide backend selection and package-wide install\u002Fimport diagnosis\n  belong to the root route; this sub-skill owns Torch-specific composition.\n\n## Completion checklist\n\nBefore handing a workflow to a researcher, verify: `torch` and `skrl` import;\nall model dictionary keys are exact; each model's input\u002Foutput role is\ncompatible with the space; the memory device and environment count agree; the\ntrainer config has finite, intentional `timesteps`; logging\u002Fcheckpoint paths\nare explicitly chosen; and resume\u002Fevaluation uses an architecture-compatible\nagent. A CPU smoke establishes import and CPU behavior only—it does **not**\nprove CUDA or another accelerator.\n","# Torch agent training\n\nUse this route for a **single-agent PyTorch** skrl 2.1.0 workflow: choose an\nalgorithm, build its model-role dictionary, allocate rollout\u002Freplay memory,\nconfigure preprocessors\u002Fnoises\u002Fschedulers, select a trainer, and make a safe\ntrain\u002Fevaluate\u002Fresume plan. Start with the bounded component check in\n[`scripts\u002Ftorch_ppo_components.py`](scripts\u002Ftorch_ppo_components.py), then use\nthe references for the exact role keys and construction details.\n\n## Route quickly\n\n1. Establish the observation, optional state, and action spaces through the\n   environment route; this skill does not choose or implement Gymnasium\n   wrappers. See [`..\u002F..\u002Freferences\u002Fframework-selection.md`](..\u002F..\u002Freferences\u002Fframework-selection.md)\n   and [`..\u002F..\u002Freferences\u002Ftroubleshooting.md`](..\u002F..\u002Freferences\u002Ftroubleshooting.md)\n   in the root skill before committing to a backend or trainer.\n2. Choose an algorithm and its required model roles in\n   [`references\u002Falgorithm-and-component-selection.md`](references\u002Falgorithm-and-component-selection.md).\n   Match the policy distribution to the action space and use a deterministic\n   value\u002Fcritic model where the table requires it.\n3. Compose the models, `RandomMemory` (when required), configuration, and agent\n   using [`references\u002Fworkflow-and-api.md`](references\u002Fworkflow-and-api.md).\n   Keep `memory_size` and the agent's rollout\u002Fupdate settings consistent.\n4. Use `SequentialTrainer` for the normal loop, `StepTrainer` when the caller\n   owns each iteration, and `ParallelTrainer` only after checking its process,\n   pickling, shared-memory, and hardware constraints.\n5. Disable writes during a smoke\u002Fevaluation probe, load a checkpoint into an\n   architecture-equivalent agent, and only then enable training or logging.\n   Check workflow-specific failure modes in\n   [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md).\n\n## Boundaries\n\n- **Environment wrappers and space conversion:** route to the\n  [`environment-integration`](..\u002F..\u002Fsub-skills\u002Fenvironment-integration\u002FSKILL.md)\n  sibling.\n- **IPPO\u002FMAPPO, multi-agent trainers, and Runner\u002FYAML:** route to\n  [`..\u002F..\u002Fsub-skills\u002Fmulti-agent-and-runner\u002FSKILL.md`](..\u002F..\u002Fsub-skills\u002Fmulti-agent-and-runner\u002FSKILL.md).\n- **JAX and Warp:** not covered here.\n- Framework-wide backend selection and package-wide install\u002Fimport diagnosis\n  belong to the root route; this sub-skill owns Torch-specific composition.\n\n## Completion checklist\n\nBefore handing a workflow to a researcher, verify: `torch` and `skrl` import;\nall model dictionary keys are exact; each model's input\u002Foutput role is\ncompatible with the space; the memory device and environment count agree; the\ntrainer config has finite, intentional `timesteps`; logging\u002Fcheckpoint paths\nare explicitly chosen; and resume\u002Fevaluation uses an architecture-compatible\nagent. A CPU smoke establishes import and CPU behavior only—it does **not**\nprove CUDA or another accelerator.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fskrl\u002Fsub-skills\u002Ftorch-agent-training",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 torch-agent-training",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill torch-agent-training",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill torch-agent-training","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fskrl\u002Fsub-skills\u002Ftorch-agent-training\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Falgorithm-and-component-selection.md","REFERENCE","参考文档",9720,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fskrl\u002Fsub-skills\u002Ftorch-agent-training\u002Freferences\u002Falgorithm-and-component-selection.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",10232,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fskrl\u002Fsub-skills\u002Ftorch-agent-training\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflow-and-api.md",11645,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fskrl\u002Fsub-skills\u002Ftorch-agent-training\u002Freferences\u002Fworkflow-and-api.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Ftorch_ppo_components.py","SCRIPT","脚本",5129,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fskrl\u002Fsub-skills\u002Ftorch-agent-training\u002Fscripts\u002Ftorch_ppo_components.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",[],[]]