{"adoption": {"forks": 669, "observed_at": "2026-08-28T04:08:57.747937+00:00", "stars": 4737}, "canonical_url": "https://ross.abutalabs.com/products/andri27-ts-reinforcement-learning", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Learn Deep Reinforcement Learning in 60 days! Lectures & Code in Python. Reinforcement Learning + Deep Learning", "domain": ["reinforcement-learning", "deep-learning", "machine-learning", "tutorials", "artificial-intelligence"], "enriched": true, "function": ["reinforcement-learning", "deep-learning", "machine-learning"], "health_score": 20, "homepage": "https://andri27-ts.github.io/Reinforcement-Learning/", "language": "Jupyter Notebook", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["andri27-ts/Reinforcement-Learning"], "name": "andri27-ts/Reinforcement-Learning", "platform": ["python", "cross-platform"], "pushed_at": "2020-06-30T11:38:42+00:00", "repo": "andri27-ts/Reinforcement-Learning", "stars": 4737, "tags": ["pytorch", "openai-gym", "dqn", "ppo", "a2c", "q-learning", "policy-gradients", "60-days-challenge", "jupyter-notebooks", "course"], "topics": ["reinforcement-learning", "machine-learning", "artificial-intelligence", "deep-reinforcement-learning", "deep-learning", "policy-gradients", "evolution-strategies", "a2c", "deepmind", "dqn", "qlearning", "ppo"], "urls": [], "use_cases": ["learn deep reinforcement learning from scratch", "find a structured RL study plan", "see PyTorch implementations of DQN and PPO", "understand actor-critic and policy gradient algorithms", "practice RL algorithms on OpenAI Gym environments", "follow a 60-day reinforcement learning challenge"], "what_it_is": "A 60-day structured course for learning Deep Reinforcement Learning, combining curated lectures (mainly from DeepMind and Berkeley) with PyTorch implementations of core algorithms like DQN, A2C, and PPO. Code is tested on OpenAI Gym environments including Atari and RoboSchool.", "when_to_avoid": ["you need a production-ready RL library or framework", "you want actively maintained code with recent updates (last release 2020)", "you are a complete beginner without ML or deep learning background"], "when_to_choose": ["you want a guided, time-boxed curriculum for deep RL", "you prefer learning by reading lectures and reading clean PyTorch code", "you already know basic Python, PyTorch, and deep learning fundamentals"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/andri27-ts-reinforcement-learning", "repo": "andri27-ts/Reinforcement-Learning", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.747937+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:18:59.022507+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc04a7c262f3cd478f6eed2c1acef5658eab89ebd8c3666345805683507eb286", "fetched_at": "2026-08-28T04:08:57.747937+00:00", "kind": "readme", "missing": false, "url": "https://github.com/andri27-ts/Reinforcement-Learning"}, {"content_hash": "e0592b56f61179c8fedebddff1fe234638b4500559163ae4f999509658837650", "fetched_at": "2026-08-29T09:02:31.546673+00:00", "kind": "homepage", "missing": false, "url": "https://andri27-ts.github.io/Reinforcement-Learning/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.747937+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:18:59.022507+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc04a7c262f3cd478f6eed2c1acef5658eab89ebd8c3666345805683507eb286", "fetched_at": "2026-08-28T04:08:57.747937+00:00", "kind": "readme", "missing": false, "url": "https://github.com/andri27-ts/Reinforcement-Learning"}, {"content_hash": "e0592b56f61179c8fedebddff1fe234638b4500559163ae4f999509658837650", "fetched_at": "2026-08-29T09:02:31.546673+00:00", "kind": "homepage", "missing": false, "url": "https://andri27-ts.github.io/Reinforcement-Learning/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:18:59.022507+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc04a7c262f3cd478f6eed2c1acef5658eab89ebd8c3666345805683507eb286", "fetched_at": "2026-08-28T04:08:57.747937+00:00", "kind": "readme", "missing": false, "url": "https://github.com/andri27-ts/Reinforcement-Learning"}, {"content_hash": "e0592b56f61179c8fedebddff1fe234638b4500559163ae4f999509658837650", "fetched_at": "2026-08-29T09:02:31.546673+00:00", "kind": "homepage", "missing": false, "url": "https://andri27-ts.github.io/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": "2026-08-28T04:08:57.747937+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.747937+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.747937+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:18:59.022507+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc04a7c262f3cd478f6eed2c1acef5658eab89ebd8c3666345805683507eb286", "fetched_at": "2026-08-28T04:08:57.747937+00:00", "kind": "readme", "missing": false, "url": "https://github.com/andri27-ts/Reinforcement-Learning"}, {"content_hash": "e0592b56f61179c8fedebddff1fe234638b4500559163ae4f999509658837650", "fetched_at": "2026-08-29T09:02:31.546673+00:00", "kind": "homepage", "missing": false, "url": "https://andri27-ts.github.io/Reinforcement-Learning/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.747937+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.747937+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:18:59.022507+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc04a7c262f3cd478f6eed2c1acef5658eab89ebd8c3666345805683507eb286", "fetched_at": "2026-08-28T04:08:57.747937+00:00", "kind": "readme", "missing": false, "url": "https://github.com/andri27-ts/Reinforcement-Learning"}, {"content_hash": "e0592b56f61179c8fedebddff1fe234638b4500559163ae4f999509658837650", "fetched_at": "2026-08-29T09:02:31.546673+00:00", "kind": "homepage", "missing": false, "url": "https://andri27-ts.github.io/Reinforcement-Learning/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.747937+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.747937+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.747937+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:18:59.022507+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc04a7c262f3cd478f6eed2c1acef5658eab89ebd8c3666345805683507eb286", "fetched_at": "2026-08-28T04:08:57.747937+00:00", "kind": "readme", "missing": false, "url": "https://github.com/andri27-ts/Reinforcement-Learning"}, {"content_hash": "e0592b56f61179c8fedebddff1fe234638b4500559163ae4f999509658837650", "fetched_at": "2026-08-29T09:02:31.546673+00:00", "kind": "homepage", "missing": false, "url": "https://andri27-ts.github.io/Reinforcement-Learning/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.747937+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:57.747937+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:18:59.022507+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc04a7c262f3cd478f6eed2c1acef5658eab89ebd8c3666345805683507eb286", "fetched_at": "2026-08-28T04:08:57.747937+00:00", "kind": "readme", "missing": false, "url": "https://github.com/andri27-ts/Reinforcement-Learning"}, {"content_hash": "e0592b56f61179c8fedebddff1fe234638b4500559163ae4f999509658837650", "fetched_at": "2026-08-29T09:02:31.546673+00:00", "kind": "homepage", "missing": false, "url": "https://andri27-ts.github.io/Reinforcement-Learning/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:18:59.022507+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc04a7c262f3cd478f6eed2c1acef5658eab89ebd8c3666345805683507eb286", "fetched_at": "2026-08-28T04:08:57.747937+00:00", "kind": "readme", "missing": false, "url": "https://github.com/andri27-ts/Reinforcement-Learning"}, {"content_hash": "e0592b56f61179c8fedebddff1fe234638b4500559163ae4f999509658837650", "fetched_at": "2026-08-29T09:02:31.546673+00:00", "kind": "homepage", "missing": false, "url": "https://andri27-ts.github.io/Reinforcement-Learning/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:18:59.022507+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc04a7c262f3cd478f6eed2c1acef5658eab89ebd8c3666345805683507eb286", "fetched_at": "2026-08-28T04:08:57.747937+00:00", "kind": "readme", "missing": false, "url": "https://github.com/andri27-ts/Reinforcement-Learning"}, {"content_hash": "e0592b56f61179c8fedebddff1fe234638b4500559163ae4f999509658837650", "fetched_at": "2026-08-29T09:02:31.546673+00:00", "kind": "homepage", "missing": false, "url": "https://andri27-ts.github.io/Reinforcement-Learning/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:18:59.022507+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc04a7c262f3cd478f6eed2c1acef5658eab89ebd8c3666345805683507eb286", "fetched_at": "2026-08-28T04:08:57.747937+00:00", "kind": "readme", "missing": false, "url": "https://github.com/andri27-ts/Reinforcement-Learning"}, {"content_hash": "e0592b56f61179c8fedebddff1fe234638b4500559163ae4f999509658837650", "fetched_at": "2026-08-29T09:02:31.546673+00:00", "kind": "homepage", "missing": false, "url": "https://andri27-ts.github.io/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": 2927, "days_push": 2255, "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}}