{"adoption": {"forks": 6122, "observed_at": "2026-08-28T04:11:32.387667+00:00", "stars": 22116}, "canonical_url": "https://ross.abutalabs.com/products/reinforcement-learning", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.", "domain": ["reinforcement-learning", "machine-learning", "deep-learning", "education", "tutorials"], "enriched": true, "function": ["reinforcement-learning", "machine-learning", "deep-learning", "data-science"], "health_score": 20, "homepage": "http://www.wildml.com/2016/10/learning-reinforcement-learning/", "language": "Jupyter Notebook", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["dennybritz/reinforcement-learning"], "name": "dennybritz/reinforcement-learning", "platform": ["python", "cross-platform"], "pushed_at": "2023-07-13T09:52:27+00:00", "repo": "dennybritz/reinforcement-learning", "stars": 22116, "tags": ["jupyter-notebooks", "openai-gym", "tensorflow", "sutton-barto", "david-silver-course", "q-learning", "policy-gradient", "exercises-and-solutions"], "topics": [], "urls": [], "use_cases": ["learn reinforcement learning algorithms with hands-on code", "find solutions to Sutton and Barto textbook exercises", "implement Q-learning and SARSA from scratch", "study deep Q-learning for Atari games", "understand policy gradient and actor-critic methods", "practice with OpenAI Gym environments", "supplement David Silver's RL course with code"], "what_it_is": "A collection of Jupyter Notebook implementations, exercises, and solutions for popular reinforcement learning algorithms, designed to accompany Sutton & Barto's textbook and David Silver's course. Code is written in Python 3 using OpenAI Gym environments and TensorFlow for deep RL methods like DQN and actor-critic.", "when_to_avoid": ["you need a production-ready RL library or framework", "you want the latest state-of-the-art algorithms like PPO or SAC", "you need actively maintained code with current dependency versions"], "when_to_choose": ["you want worked notebook examples alongside classic RL theory materials", "you need reference implementations of tabular and deep RL algorithms", "you're following Sutton's book or Silver's course and want coding practice"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/reinforcement-learning", "repo": "dennybritz/reinforcement-learning", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.387667+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:57:43.008322+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fe2ef4fd510ecca587c928d406d61ef6865708c7c18c13af6fbceb8dd061da49", "fetched_at": "2026-08-28T04:11:32.387667+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dennybritz/reinforcement-learning"}, {"content_hash": "bf86b6172d5a8e7cb7110f811cc3540a8297b0263f566b89c6e68377ff778cb0", "fetched_at": "2026-08-29T07:55:55.202896+00:00", "kind": "homepage", "missing": false, "url": "http://www.wildml.com/2016/10/learning-reinforcement-learning/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.387667+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:57:43.008322+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fe2ef4fd510ecca587c928d406d61ef6865708c7c18c13af6fbceb8dd061da49", "fetched_at": "2026-08-28T04:11:32.387667+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dennybritz/reinforcement-learning"}, {"content_hash": "bf86b6172d5a8e7cb7110f811cc3540a8297b0263f566b89c6e68377ff778cb0", "fetched_at": "2026-08-29T07:55:55.202896+00:00", "kind": "homepage", "missing": false, "url": "http://www.wildml.com/2016/10/learning-reinforcement-learning/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:57:43.008322+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fe2ef4fd510ecca587c928d406d61ef6865708c7c18c13af6fbceb8dd061da49", "fetched_at": "2026-08-28T04:11:32.387667+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dennybritz/reinforcement-learning"}, {"content_hash": "bf86b6172d5a8e7cb7110f811cc3540a8297b0263f566b89c6e68377ff778cb0", "fetched_at": "2026-08-29T07:55:55.202896+00:00", "kind": "homepage", "missing": false, "url": "http://www.wildml.com/2016/10/learning-reinforcement-learning/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.387667+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.387667+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.387667+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:57:43.008322+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fe2ef4fd510ecca587c928d406d61ef6865708c7c18c13af6fbceb8dd061da49", "fetched_at": "2026-08-28T04:11:32.387667+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dennybritz/reinforcement-learning"}, {"content_hash": "bf86b6172d5a8e7cb7110f811cc3540a8297b0263f566b89c6e68377ff778cb0", "fetched_at": "2026-08-29T07:55:55.202896+00:00", "kind": "homepage", "missing": false, "url": "http://www.wildml.com/2016/10/learning-reinforcement-learning/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.387667+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.387667+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:57:43.008322+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fe2ef4fd510ecca587c928d406d61ef6865708c7c18c13af6fbceb8dd061da49", "fetched_at": "2026-08-28T04:11:32.387667+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dennybritz/reinforcement-learning"}, {"content_hash": "bf86b6172d5a8e7cb7110f811cc3540a8297b0263f566b89c6e68377ff778cb0", "fetched_at": "2026-08-29T07:55:55.202896+00:00", "kind": "homepage", "missing": false, "url": "http://www.wildml.com/2016/10/learning-reinforcement-learning/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.387667+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.387667+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.387667+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:57:43.008322+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fe2ef4fd510ecca587c928d406d61ef6865708c7c18c13af6fbceb8dd061da49", "fetched_at": "2026-08-28T04:11:32.387667+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dennybritz/reinforcement-learning"}, {"content_hash": "bf86b6172d5a8e7cb7110f811cc3540a8297b0263f566b89c6e68377ff778cb0", "fetched_at": "2026-08-29T07:55:55.202896+00:00", "kind": "homepage", "missing": false, "url": "http://www.wildml.com/2016/10/learning-reinforcement-learning/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.387667+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:11:32.387667+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:57:43.008322+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fe2ef4fd510ecca587c928d406d61ef6865708c7c18c13af6fbceb8dd061da49", "fetched_at": "2026-08-28T04:11:32.387667+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dennybritz/reinforcement-learning"}, {"content_hash": "bf86b6172d5a8e7cb7110f811cc3540a8297b0263f566b89c6e68377ff778cb0", "fetched_at": "2026-08-29T07:55:55.202896+00:00", "kind": "homepage", "missing": false, "url": "http://www.wildml.com/2016/10/learning-reinforcement-learning/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:57:43.008322+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fe2ef4fd510ecca587c928d406d61ef6865708c7c18c13af6fbceb8dd061da49", "fetched_at": "2026-08-28T04:11:32.387667+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dennybritz/reinforcement-learning"}, {"content_hash": "bf86b6172d5a8e7cb7110f811cc3540a8297b0263f566b89c6e68377ff778cb0", "fetched_at": "2026-08-29T07:55:55.202896+00:00", "kind": "homepage", "missing": false, "url": "http://www.wildml.com/2016/10/learning-reinforcement-learning/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:57:43.008322+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fe2ef4fd510ecca587c928d406d61ef6865708c7c18c13af6fbceb8dd061da49", "fetched_at": "2026-08-28T04:11:32.387667+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dennybritz/reinforcement-learning"}, {"content_hash": "bf86b6172d5a8e7cb7110f811cc3540a8297b0263f566b89c6e68377ff778cb0", "fetched_at": "2026-08-29T07:55:55.202896+00:00", "kind": "homepage", "missing": false, "url": "http://www.wildml.com/2016/10/learning-reinforcement-learning/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:57:43.008322+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fe2ef4fd510ecca587c928d406d61ef6865708c7c18c13af6fbceb8dd061da49", "fetched_at": "2026-08-28T04:11:32.387667+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dennybritz/reinforcement-learning"}, {"content_hash": "bf86b6172d5a8e7cb7110f811cc3540a8297b0263f566b89c6e68377ff778cb0", "fetched_at": "2026-08-29T07:55:55.202896+00:00", "kind": "homepage", "missing": false, "url": "http://www.wildml.com/2016/10/learning-reinforcement-learning/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "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": 3661, "days_push": 1147, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}