[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78S893H6NVB44F02MPVVTTR":3,"skill-same:01M78S893H6NVB44F02MPVVTTR":71},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M78S893H6NVB44F02MPVVTTR","offline-bandits-data",null,"Use AgileRL offline RL datasets, replay\u002Fdata conversion, CQL\u002FILQL, contextual bandits, NeuralUCB\u002FNeuralTS, and BanditEnv workflows.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fagilerl\u002Fsub-skills\u002Foffline-bandits-data\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: offline-bandits-data\ndescription: \"Use AgileRL offline RL datasets, replay\u002Fdata conversion, CQL\u002FILQL,\n  contextual bandits, NeuralUCB\u002FNeuralTS, and BanditEnv workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# AgileRL Offline RL And Bandit Data\n\nUse this sub-skill for AgileRL offline reinforcement learning, replay\u002Fdata conversion, `CQL`, `ILQL`, `train_offline`, contextual bandits, `NeuralUCB`, `NeuralTS`, and `BanditEnv` workflows.\n\n## Read First\n\n- `references\u002Fworkflows.md` for offline RL and contextual bandit recipes.\n- `references\u002Fdata-formats.md` for transition, HDF5\u002FMinari, and tabular bandit schemas.\n- `references\u002Fapi-reference.md` for replay\u002Fbandit\u002Foffline APIs.\n- `references\u002Ftroubleshooting.md` for shape, schema, and network\u002Fdownload failures.\n- `scripts\u002Finspect_bandit_setup.py --help` for a no-download synthetic bandit probe.\n\n## Boundaries\n\n- Use `..\u002Ftraining-workflows\u002FSKILL.md` for online Gymnasium PPO\u002FDQN\u002FDDPG\u002FTD3 workflows.\n- Use `..\u002Fhpo-and-mutation\u002FSKILL.md` for tournament\u002Fmutation configuration.\n- Use `..\u002Fllm-fine-tuning\u002FSKILL.md` for language\u002FLLM datasets and RL post-training environments.\n- This sub-skill owns static transition datasets, replay filling, Minari\u002FHDF5 handling, and one-step contextual bandit datasets.\n\n## Offline RL Flow\n\n1. Load or validate a dataset with observations, actions, rewards, next observations, and done\u002Fterminal flags.\n2. Create an environment only for spaces\u002Fevaluation, not online data collection.\n3. Create a `CQN`\u002F`ILQL`-style population with `create_population(...)`.\n4. Fill `ReplayBuffer` with `Transition(...).to_tensordict()` entries.\n5. Configure HPO and call `train_offline(...)` or a custom offline loop.\n\n## Contextual Bandit Flow\n\n1. Prepare tabular or array features and targets.\n2. Create `BanditEnv(features, targets)`.\n3. Use `NeuralUCB` or `NeuralTS` with a discrete action space.\n4. Use replay memory and `train_bandits(...)` or a custom one-step loop.\n\n## Safe Validation\n\n```bash\npython scripts\u002Finspect_bandit_setup.py --rows 8 --features 4 --arms 3\n```\n\nThe helper creates synthetic in-memory data. It does not download UCI datasets or run training.\n","# AgileRL Offline RL And Bandit Data\n\nUse this sub-skill for AgileRL offline reinforcement learning, replay\u002Fdata conversion, `CQL`, `ILQL`, `train_offline`, contextual bandits, `NeuralUCB`, `NeuralTS`, and `BanditEnv` workflows.\n\n## Read First\n\n- `references\u002Fworkflows.md` for offline RL and contextual bandit recipes.\n- `references\u002Fdata-formats.md` for transition, HDF5\u002FMinari, and tabular bandit schemas.\n- `references\u002Fapi-reference.md` for replay\u002Fbandit\u002Foffline APIs.\n- `references\u002Ftroubleshooting.md` for shape, schema, and network\u002Fdownload failures.\n- `scripts\u002Finspect_bandit_setup.py --help` for a no-download synthetic bandit probe.\n\n## Boundaries\n\n- Use `..\u002Ftraining-workflows\u002FSKILL.md` for online Gymnasium PPO\u002FDQN\u002FDDPG\u002FTD3 workflows.\n- Use `..\u002Fhpo-and-mutation\u002FSKILL.md` for tournament\u002Fmutation configuration.\n- Use `..\u002Fllm-fine-tuning\u002FSKILL.md` for language\u002FLLM datasets and RL post-training environments.\n- This sub-skill owns static transition datasets, replay filling, Minari\u002FHDF5 handling, and one-step contextual bandit datasets.\n\n## Offline RL Flow\n\n1. Load or validate a dataset with observations, actions, rewards, next observations, and done\u002Fterminal flags.\n2. Create an environment only for spaces\u002Fevaluation, not online data collection.\n3. Create a `CQN`\u002F`ILQL`-style population with `create_population(...)`.\n4. Fill `ReplayBuffer` with `Transition(...).to_tensordict()` entries.\n5. Configure HPO and call `train_offline(...)` or a custom offline loop.\n\n## Contextual Bandit Flow\n\n1. Prepare tabular or array features and targets.\n2. Create `BanditEnv(features, targets)`.\n3. Use `NeuralUCB` or `NeuralTS` with a discrete action space.\n4. Use replay memory and `train_bandits(...)` or a custom one-step loop.\n\n## Safe Validation\n\n```bash\npython scripts\u002Finspect_bandit_setup.py --rows 8 --features 4 --arms 3\n```\n\nThe helper creates synthetic in-memory data. It does not download UCI datasets or run training.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fagilerl\u002Fsub-skills\u002Foffline-bandits-data",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill offline-bandits-data",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill offline-bandits-data",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill offline-bandits-data","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fagilerl\u002Fsub-skills\u002Foffline-bandits-data\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",1050,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fagilerl\u002Fsub-skills\u002Foffline-bandits-data\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fdata-formats.md",1504,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fagilerl\u002Fsub-skills\u002Foffline-bandits-data\u002Freferences\u002Fdata-formats.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",1253,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fagilerl\u002Fsub-skills\u002Foffline-bandits-data\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fworkflows.md",1796,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fagilerl\u002Fsub-skills\u002Foffline-bandits-data\u002Freferences\u002Fworkflows.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Finspect_bandit_setup.py","SCRIPT","脚本",2025,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fagilerl\u002Fsub-skills\u002Foffline-bandits-data\u002Fscripts\u002Finspect_bandit_setup.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]