{"adoption": {"forks": 258, "observed_at": "2026-08-28T04:08:48.788535+00:00", "stars": 4422}, "canonical_url": "https://ross.abutalabs.com/products/awesome-rlhf", "card": {"archived": false, "artifact_type": "learning-resource", "description": "A curated list of reinforcement learning with human feedback resources (continually updated)", "domain": ["reinforcement-learning", "large-language-models", "machine-learning", "artificial-intelligence", "tutorials"], "enriched": true, "function": ["reinforcement-learning", "llm-training", "machine-learning"], "health_score": 70, "homepage": null, "language": null, "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["opendilab/awesome-RLHF"], "name": "opendilab/awesome-RLHF", "platform": ["cross-platform"], "pushed_at": "2026-05-20T12:56:15+00:00", "repo": "opendilab/awesome-RLHF", "stars": 4422, "tags": ["awesome-list", "rlhf", "curated-list", "research-papers", "human-feedback", "alignment"], "topics": ["deep-learning", "deep-reinforcement-learning", "human-feedback", "reinforcement-learning", "rlhf", "large-language-models"], "urls": [], "use_cases": ["find papers on RLHF for LLM alignment", "learn how reinforcement learning with human feedback works", "find open-source RLHF codebases and datasets", "track the latest RLHF research in 2024-2026", "study reward modeling and human preference learning", "get reading material for aligning language models with human values"], "what_it_is": "A curated, continually updated list of research papers, codebases, datasets, blogs, and books about Reinforcement Learning with Human Feedback (RLHF). It tracks the frontier of RLHF for both large language models and applications like video games.", "when_to_avoid": ["you need runnable RLHF training code rather than a resource list", "you need a maintained software library with an API", "you need non-RLHF reinforcement learning resources"], "when_to_choose": ["you need a starting point to survey the RLHF literature", "you want curated links to papers, code, and datasets in one place", "you are researching LLM alignment or preference-based RL"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/awesome-rlhf", "repo": "opendilab/awesome-RLHF", "role": "main", "score": 68}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:48.788535+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:20:58.585061+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "76d0ad05abfd55abc799f2522aa4553bd59edb6557d6c4738f4ec79d2356d1f1", "fetched_at": "2026-08-28T04:08:48.788535+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendilab/awesome-RLHF"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:48.788535+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:20:58.585061+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "76d0ad05abfd55abc799f2522aa4553bd59edb6557d6c4738f4ec79d2356d1f1", "fetched_at": "2026-08-28T04:08:48.788535+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendilab/awesome-RLHF"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:20:58.585061+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "76d0ad05abfd55abc799f2522aa4553bd59edb6557d6c4738f4ec79d2356d1f1", "fetched_at": "2026-08-28T04:08:48.788535+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendilab/awesome-RLHF"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:48.788535+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:48.788535+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:48.788535+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:20:58.585061+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "76d0ad05abfd55abc799f2522aa4553bd59edb6557d6c4738f4ec79d2356d1f1", "fetched_at": "2026-08-28T04:08:48.788535+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendilab/awesome-RLHF"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:48.788535+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:48.788535+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:20:58.585061+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "76d0ad05abfd55abc799f2522aa4553bd59edb6557d6c4738f4ec79d2356d1f1", "fetched_at": "2026-08-28T04:08:48.788535+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendilab/awesome-RLHF"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:48.788535+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:48.788535+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:48.788535+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:20:58.585061+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "76d0ad05abfd55abc799f2522aa4553bd59edb6557d6c4738f4ec79d2356d1f1", "fetched_at": "2026-08-28T04:08:48.788535+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendilab/awesome-RLHF"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:48.788535+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:48.788535+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:20:58.585061+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "76d0ad05abfd55abc799f2522aa4553bd59edb6557d6c4738f4ec79d2356d1f1", "fetched_at": "2026-08-28T04:08:48.788535+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendilab/awesome-RLHF"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:20:58.585061+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "76d0ad05abfd55abc799f2522aa4553bd59edb6557d6c4738f4ec79d2356d1f1", "fetched_at": "2026-08-28T04:08:48.788535+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendilab/awesome-RLHF"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:20:58.585061+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "76d0ad05abfd55abc799f2522aa4553bd59edb6557d6c4738f4ec79d2356d1f1", "fetched_at": "2026-08-28T04:08:48.788535+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendilab/awesome-RLHF"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:20:58.585061+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "76d0ad05abfd55abc799f2522aa4553bd59edb6557d6c4738f4ec79d2356d1f1", "fetched_at": "2026-08-28T04:08:48.788535+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendilab/awesome-RLHF"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 83, "longevity": 92, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1297, "days_push": 105, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 68, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}