[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EWNBWPX6ASE66M4F9Q79AH":3,"skill-same:01M7EWNBWPX6ASE66M4F9Q79AH":71},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":48},"01M7EWNBWPX6ASE66M4F9Q79AH","training-workflows",null,"Use AgileRL classical single-agent training workflows for Gymnasium PPO, DQN, RainbowDQN, DDPG, TD3, replay\u002Frollout buffers, and distributed training setup.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fagilerl\u002Fsub-skills\u002Ftraining-workflows\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: training-workflows\ndescription: \"Use AgileRL classical single-agent training workflows for\n  Gymnasium PPO, DQN, RainbowDQN, DDPG, TD3, replay\u002Frollout buffers, and\n  distributed training setup.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# AgileRL Training Workflows\n\nUse this sub-skill for AgileRL classical single-agent RL training with Gymnasium environments: PPO on-policy, DQN\u002FRainbowDQN\u002FDDPG\u002FTD3 off-policy, recurrent variants, population setup, replay or rollout buffers, and safe pre-flight checks before long runs.\n\n## Read First\n\n- `references\u002Fworkflows.md` for on-policy\u002Foff-policy training recipes and population flow.\n- `references\u002Fapi-reference.md` for important training helper and buffer APIs.\n- `references\u002Fconfiguration.md` for `INIT_HP`, `net_config`, YAML, logging, and environment patterns.\n- `references\u002Fdistributed-training.md` for Accelerate\u002Fdistributed constraints.\n- `references\u002Ftroubleshooting.md` for shape, dependency, vector-env, W&B, and runtime failures.\n- `scripts\u002Fagilerl_classic_smoke.py --help` for a no-training import\u002Fconfig probe.\n\n## Route Within AgileRL\n\n| Need | Route |\n| --- | --- |\n| Evolution\u002Ftournament\u002Fmutation configuration | `..\u002Fhpo-and-mutation\u002FSKILL.md` |\n| Custom `net_config`, `EvolvableNetwork`, CNN\u002FLSTM\u002FMultiInput setup | `..\u002Fevolvable-modules\u002FSKILL.md` |\n| Multi-agent PettingZoo training | `..\u002Fmulti-agent-and-wrappers\u002FSKILL.md` |\n| Offline datasets or contextual bandits | `..\u002Foffline-bandits-data\u002FSKILL.md` |\n| LLM fine-tuning | `..\u002Fllm-fine-tuning\u002FSKILL.md` |\n\n## Standard Classical Training Flow\n\n1. Install AgileRL and verify imports; use the root `scripts\u002Fcheck_agilerl_install.py` if unsure.\n2. Create or wrap a Gymnasium environment; prefer `make_vect_envs(env_name, num_envs=...)` for vectorized classical training.\n3. Define `INIT_HP` with algorithm-specific keys and `POP_SIZE`.\n4. Define `net_config` with `encoder_config` and `head_config` unless the default network is sufficient.\n5. Create a population with `create_population(algo=..., observation_space=..., action_space=..., net_config=..., INIT_HP=..., population_size=..., num_envs=..., device=...)`.\n6. For off-policy algorithms, create `ReplayBuffer`; for on-policy PPO, use rollout collection\u002Ftraining helpers rather than replay memory.\n7. Configure `TournamentSelection` and `Mutations` in the HPO sub-skill.\n8. Call `train_on_policy(...)` or `train_off_policy(...)`, or implement a custom loop following `references\u002Fworkflows.md`.\n\n## Algorithm Selection\n\n- Use `PPO` for on-policy, stable policy-gradient workflows and recurrent PPO variants.\n- Use `DQN` or `RainbowDQN` for discrete-action off-policy value learning.\n- Use `DDPG` or `TD3` for continuous-action off-policy actor-critic workflows.\n- Use `train_on_policy` for PPO and `train_off_policy` for DQN\u002FRainbowDQN\u002FDDPG\u002FTD3 families.\n\n## Safe Validation\n\nRun a smoke check before training:\n\n```bash\npython scripts\u002Fagilerl_classic_smoke.py --algorithm DQN --env CartPole-v1\npython scripts\u002Fagilerl_classic_smoke.py --algorithm PPO --env CartPole-v1\n```\n\nThe helper checks imports, Gymnasium spaces, basic config shape, and algorithm family routing. It does not train or download anything.\n","# AgileRL Training Workflows\n\nUse this sub-skill for AgileRL classical single-agent RL training with Gymnasium environments: PPO on-policy, DQN\u002FRainbowDQN\u002FDDPG\u002FTD3 off-policy, recurrent variants, population setup, replay or rollout buffers, and safe pre-flight checks before long runs.\n\n## Read First\n\n- `references\u002Fworkflows.md` for on-policy\u002Foff-policy training recipes and population flow.\n- `references\u002Fapi-reference.md` for important training helper and buffer APIs.\n- `references\u002Fconfiguration.md` for `INIT_HP`, `net_config`, YAML, logging, and environment patterns.\n- `references\u002Fdistributed-training.md` for Accelerate\u002Fdistributed constraints.\n- `references\u002Ftroubleshooting.md` for shape, dependency, vector-env, W&B, and runtime failures.\n- `scripts\u002Fagilerl_classic_smoke.py --help` for a no-training import\u002Fconfig probe.\n\n## Route Within AgileRL\n\n| Need | Route |\n| --- | --- |\n| Evolution\u002Ftournament\u002Fmutation configuration | `..\u002Fhpo-and-mutation\u002FSKILL.md` |\n| Custom `net_config`, `EvolvableNetwork`, CNN\u002FLSTM\u002FMultiInput setup | `..\u002Fevolvable-modules\u002FSKILL.md` |\n| Multi-agent PettingZoo training | `..\u002Fmulti-agent-and-wrappers\u002FSKILL.md` |\n| Offline datasets or contextual bandits | `..\u002Foffline-bandits-data\u002FSKILL.md` |\n| LLM fine-tuning | `..\u002Fllm-fine-tuning\u002FSKILL.md` |\n\n## Standard Classical Training Flow\n\n1. Install AgileRL and verify imports; use the root `scripts\u002Fcheck_agilerl_install.py` if unsure.\n2. Create or wrap a Gymnasium environment; prefer `make_vect_envs(env_name, num_envs=...)` for vectorized classical training.\n3. Define `INIT_HP` with algorithm-specific keys and `POP_SIZE`.\n4. Define `net_config` with `encoder_config` and `head_config` unless the default network is sufficient.\n5. Create a population with `create_population(algo=..., observation_space=..., action_space=..., net_config=..., INIT_HP=..., population_size=..., num_envs=..., device=...)`.\n6. For off-policy algorithms, create `ReplayBuffer`; for on-policy PPO, use rollout collection\u002Ftraining helpers rather than replay memory.\n7. Configure `TournamentSelection` and `Mutations` in the HPO sub-skill.\n8. Call `train_on_policy(...)` or `train_off_policy(...)`, or implement a custom loop following `references\u002Fworkflows.md`.\n\n## Algorithm Selection\n\n- Use `PPO` for on-policy, stable policy-gradient workflows and recurrent PPO variants.\n- Use `DQN` or `RainbowDQN` for discrete-action off-policy value learning.\n- Use `DDPG` or `TD3` for continuous-action off-policy actor-critic workflows.\n- Use `train_on_policy` for PPO and `train_off_policy` for DQN\u002FRainbowDQN\u002FDDPG\u002FTD3 families.\n\n## Safe Validation\n\nRun a smoke check before training:\n\n```bash\npython scripts\u002Fagilerl_classic_smoke.py --algorithm DQN --env CartPole-v1\npython scripts\u002Fagilerl_classic_smoke.py --algorithm PPO --env CartPole-v1\n```\n\nThe helper checks imports, Gymnasium spaces, basic config shape, and algorithm family routing. It does not train or download anything.\n",{"name":5,"license":24,"metadata":25,"description":7,"disable-model-invocation":27},"Apache 2.0",{"disco-role":26},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fagilerl\u002Fsub-skills\u002Ftraining-workflows",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":27},[38,41,44],{"tool":39,"command":40},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill training-workflows",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill training-workflows",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill training-workflows","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fagilerl\u002Fsub-skills\u002Ftraining-workflows\u002FSKILL.md",[49,55,59,63,67],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fapi-reference.md","REFERENCE","参考文档",2287,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fagilerl\u002Fsub-skills\u002Ftraining-workflows\u002Freferences\u002Fapi-reference.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fconfiguration.md",1692,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fagilerl\u002Fsub-skills\u002Ftraining-workflows\u002Freferences\u002Fconfiguration.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fdistributed-training.md",1236,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fagilerl\u002Fsub-skills\u002Ftraining-workflows\u002Freferences\u002Fdistributed-training.md",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Ftroubleshooting.md",1740,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fagilerl\u002Fsub-skills\u002Ftraining-workflows\u002Freferences\u002Ftroubleshooting.md",{"path":68,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fworkflows.md",3214,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fagilerl\u002Fsub-skills\u002Ftraining-workflows\u002Freferences\u002Fworkflows.md",[72,81,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":80},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":82,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":80},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":80},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":80},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":80},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":80},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]