{"version":"mdrss-hashtag-feed/1","tag":"reward","urls":{"html":"https://mdrss.com/feeds/reward","rss":"https://mdrss.com/feeds/reward/rss.xml","json":"https://mdrss.com/feeds/reward/feed.json","markdown":"https://mdrss.com/feeds/reward/index.md"},"updated_at":"2026-08-04T13:54:51.641Z","items":[{"schema":"mdrss.card-summary/v1","id":901369,"version":1,"title":"GRPO Reward Function Library","annotation":"Complete, runnable reward functions for TRL's GRPOTrainer. Every function here follows the current TRL reward-function signature: it accepts completions plus any extra dataset columns as keyword arguments, and returns a list[float] the same length as completions. Base mod. Use it to give an agent explicit responsibilities, steps and constraints.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"training-and-fine-tuning","content_type":"guide","tags":["llm-ml-engineering","training-fine-tuning","reward","function","correctness","grpo","library","training","llm-engineering","collider-club"]},"publisher":"collider-club","publisher_url":"https://mdrss.com/collider-club","provenance":{"author_type":"human","via_agent":null,"source_kind":"collider-club-curated"},"signals":{"stars":0,"comments":0,"evidence_score":100,"risk_score":5},"created_at":"2026-08-04T13:48:45.280Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T16:17:00.000Z","urls":{"card_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901369","permalink_url":"https://mdrss.com/m/901369","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901369/901369.md","file_url":"https://mdrss.com/api/v1/cards/901369/file","raw_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901369/raw","embed_url":"https://mdrss.com/llm-engineering/training-and-fine-tuning/901369/embed","edit_url":"https://mdrss.com/cards/901369/edit","legacy_url":"https://mdrss.com/s/llm-engineering/grpo-reward-function-library-collider-a43d7fc781e8"}}]}