{"version":"mdrss-hashtag-feed/1","tag":"reinforcement","urls":{"html":"https://mdrss.com/feeds/reinforcement","rss":"https://mdrss.com/feeds/reinforcement/rss.xml","json":"https://mdrss.com/feeds/reinforcement/feed.json","markdown":"https://mdrss.com/feeds/reinforcement/index.md"},"updated_at":"2026-08-04T13:54:51.641Z","items":[{"schema":"mdrss.card-summary/v1","id":901071,"version":1,"title":"TRL - Transformers Reinforcement Learning","annotation":"TRL is a cutting-edge library designed for post-training foundation models using advanced techniques like Supervised Fine-Tuning (SFT), Group Relative Policy Optimization (GRPO), and Direct Preference Optimization (DPO). Built on top of the 🤗 Transformers ecosystem, TRL supports. Use it to navigate the topic and choose relevant methods, papers or tools.","catalog_feed":{"slug":"llm-engineering","url":"https://mdrss.com/s/llm-engineering"},"classification":{"domain":"llm-engineering","category":"inference-and-quantization","content_type":"reference","tags":["llm-ml-engineering","inference-and-quantization","trl","transformers","reinforcement","learning","optimization","inference","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":"2026-08-04T13:48:02.244Z","updated_at":"2026-08-04T13:54:51.641Z","snapshot_at":"2026-08-04T13:48:02.244Z","urls":{"card_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901071","permalink_url":"https://mdrss.com/m/901071","thread_url":"https://mdrss.com/s/llm-engineering","markdown_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901071/901071.md","file_url":"https://mdrss.com/api/v1/cards/901071/file","raw_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901071/raw","embed_url":"https://mdrss.com/llm-engineering/inference-and-quantization/901071/embed","edit_url":"https://mdrss.com/cards/901071/edit","legacy_url":"https://mdrss.com/s/llm-engineering/trl-transformers-reinforcement-learning-collider-d07f9474376d"}}]}