[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7994M2CF0KWN1DQSFZ41YE2":3,"skill-same:01M7994M2CF0KWN1DQSFZ41YE2":54},{"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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7994M2CF0KWN1DQSFZ41YE2","reinforce_training_loop",null,"Run bounded REINFORCE stochastic-policy training loops with sampled actions, scalar rewards, baselines, and optimizer traces.","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\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fsapg\u002Fskill\u002Freinforce_policy_gradient\u002Freinforce_training_loop\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: reinforce_training_loop\ndescription: Run bounded REINFORCE stochastic-policy training loops with sampled actions, scalar rewards, baselines, and optimizer traces.\n---\n\n# REINFORCE Training Loop\n\nUse this skill to recover or test Williams-style REINFORCE behavior on a small stochastic environment. It is appropriate when the evidence must show sampled stochastic actions, scalar reinforcement, score-function updates, and changed policy parameters. Do not use it for deterministic policy-gradient, Q-learning, or supervised imitation-only experiments.\n\n## Inputs\n\n- Initial Bernoulli logit or equivalent stochastic policy parameters.\n- Reward function mapping sampled actions to scalar rewards.\n- Episode count, learning rate, random seed, and baseline value.\n- Optional path to the `score_function_estimator` script for cross-checking the local score term.\n\n## Outputs\n\n- Episode-level trace containing action probability, sampled action, reward, advantage, update, and parameter value.\n- Summary metrics before and after training.\n- `params_before` and `params_after` fields suitable for Distiller recovery validation.\n- Mechanism booleans for stochastic sampling and optimizer execution.\n\n## Workflow\n\n1. Initialize the stochastic policy and compute its expected reward before training.\n2. For every episode, sample an action from the current policy distribution.\n3. Observe scalar reward and compute the REINFORCE score-function update.\n4. Apply `theta += learning_rate * update` and record the parameter transition.\n5. Report expected reward after training and verify that parameters changed.\n6. When used in recovery, save the trace under `recovery\u002Flogs\u002Ftraining_trace.json`.\n\n## Validation\n\nRun:\n\n```bash\npython scripts\u002Ftrain_bandit.py --episodes 128 --seed 7 --output \u002Ftmp\u002Freinforce_trace.json\npython -m pytest tests\n```\n\nThe tests assert that the better action's probability and expected reward improve in a deterministic seeded two-action bandit.\n\n## Limitations\n\nThis skill is a reduced mechanism-faithful recovery harness. It does not claim to reproduce every historical example from the paper or delayed-reinforcement variants.\n","# REINFORCE Training Loop\n\nUse this skill to recover or test Williams-style REINFORCE behavior on a small stochastic environment. It is appropriate when the evidence must show sampled stochastic actions, scalar reinforcement, score-function updates, and changed policy parameters. Do not use it for deterministic policy-gradient, Q-learning, or supervised imitation-only experiments.\n\n## Inputs\n\n- Initial Bernoulli logit or equivalent stochastic policy parameters.\n- Reward function mapping sampled actions to scalar rewards.\n- Episode count, learning rate, random seed, and baseline value.\n- Optional path to the `score_function_estimator` script for cross-checking the local score term.\n\n## Outputs\n\n- Episode-level trace containing action probability, sampled action, reward, advantage, update, and parameter value.\n- Summary metrics before and after training.\n- `params_before` and `params_after` fields suitable for Distiller recovery validation.\n- Mechanism booleans for stochastic sampling and optimizer execution.\n\n## Workflow\n\n1. Initialize the stochastic policy and compute its expected reward before training.\n2. For every episode, sample an action from the current policy distribution.\n3. Observe scalar reward and compute the REINFORCE score-function update.\n4. Apply `theta += learning_rate * update` and record the parameter transition.\n5. Report expected reward after training and verify that parameters changed.\n6. When used in recovery, save the trace under `recovery\u002Flogs\u002Ftraining_trace.json`.\n\n## Validation\n\nRun:\n\n```bash\npython scripts\u002Ftrain_bandit.py --episodes 128 --seed 7 --output \u002Ftmp\u002Freinforce_trace.json\npython -m pytest tests\n```\n\nThe tests assert that the better action's probability and expected reward improve in a deterministic seeded two-action bandit.\n\n## Limitations\n\nThis skill is a reduced mechanism-faithful recovery harness. It does not claim to reproduce every historical example from the paper or delayed-reinforcement variants.\n",{"name":5,"description":7},"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fsapg\u002Fskill\u002Freinforce_policy_gradient\u002Freinforce_training_loop",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill reinforce_training_loop",{"tool":36,"command":37},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill reinforce_training_loop",{"tool":39,"command":40},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill reinforce_training_loop","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fsapg\u002Fskill\u002Freinforce_policy_gradient\u002Freinforce_training_loop\u002FSKILL.md",true,[44,50],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Ftrain_bandit.py","SCRIPT","脚本",4635,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fsapg\u002Fskill\u002Freinforce_policy_gradient\u002Freinforce_training_loop\u002Fscripts\u002Ftrain_bandit.py",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"tests\u002Ftest_train_bandit.py",1401,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fsapg\u002Fskill\u002Freinforce_policy_gradient\u002Freinforce_training_loop\u002Ftests\u002Ftest_train_bandit.py",[55,62,69,76,83,90],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"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":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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",[],[]]