{"data":{"slug":"opendilab-awesome-rlhf","name":"awesome-RLHF","tagline":"A curated list of reinforcement learning with human feedback resources (continually updated)","github_url":"https://github.com/opendilab/awesome-RLHF","owner":"opendilab","repo":"awesome-RLHF","owner_avatar_url":"https://avatars.githubusercontent.com/u/86840398?v=4","primary_language":null,"stars":4422,"forks":258,"topics":["deep-learning","deep-reinforcement-learning","human-feedback","large-language-models","reinforcement-learning","rlhf"],"archived":false,"github_pushed_at":"2026-05-20T12:56:15+00:00","maintenance_label":"Steady","stars_delta_30d":9,"url":"https://www.graphcanon.com/tools/opendilab-awesome-rlhf","markdown_url":"https://www.graphcanon.com/tools/opendilab-awesome-rlhf.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/opendilab-awesome-rlhf","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=opendilab-awesome-rlhf","description":"A curated list of reinforcement learning with human feedback resources (continually updated)","homepage_url":null,"license":"Apache-2.0","open_issues":6,"watchers":61,"ai_summary":"Provides a comprehensive list of resources focused on reinforcement learning enhanced with human feedback, relevant for developing and refining large language models through interactive training methods.","readme_excerpt":"## License\n\nAwesome RLHF is released under the Apache 2.0 license.","github_created_at":"2023-02-13T11:19:23+00:00","created_at":"2026-07-07T17:35:12.292185+00:00","updated_at":"2026-08-17T18:00:53.791199+00:00","categories":[{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"deep-learning","name":"deep-learning"},{"slug":"depth-reinforcement-learning","name":"depth-reinforcement-learning"},{"slug":"human-feedback","name":"human-feedback"},{"slug":"large-language-models","name":"large language models"},{"slug":"reinforcement-learning","name":"reinforcement-learning"},{"slug":"rlhf","name":"rlhf"}],"trust":{"provenance":{"is_fork":false,"github_id":601100396,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-17T18:00:51.515Z","maintenance":{"label":"Steady","score":60,"methodology":"github_public_v1","releases_90d":0,"days_since_push":89,"last_release_at":null,"stars_delta_30d":9,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:05:02.786Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-17T18:00:52.741Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-17T18:00:52.741Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you are specifically interested in the resources that pertain to enhancing reinforcement learning algorithms with human feedback for developing advanced AI systems."],"when_not_to_use":["If your focus is exclusively on generic deep-learning or reinforcement-learning resources without the aspect of integrating human feedback into the training process."],"source":"enrich:decision_facts","observed_at":"2026-07-12T18:06:09.143Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"awesome-RLHF is a curated resource list focusing on reinforcement learning with human feedback (RLHF), which is crucial for refining large language models through interactive training methods."}]}}