{"adoption": {"forks": 735, "observed_at": "2026-08-28T04:08:13.257080+00:00", "stars": 3659}, "canonical_url": "https://ross.abutalabs.com/products/rlcode-reinforcement-learning", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Minimal and Clean Reinforcement Learning Examples", "domain": ["reinforcement-learning", "machine-learning", "education", "tutorials"], "enriched": true, "function": ["reinforcement-learning", "machine-learning", "deep-learning", "benchmarking"], "health_score": 72, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["rlcode/reinforcement-learning"], "name": "rlcode/reinforcement-learning", "platform": ["python", "cross-platform"], "pushed_at": "2026-06-12T03:36:43+00:00", "repo": "rlcode/reinforcement-learning", "stars": 3659, "tags": ["dqn", "ppo", "actor-critic", "policy-gradient", "q-learning", "sarsa", "atari", "cartpole", "grid-world", "pytorch", "educational-examples", "gpu"], "topics": ["reinforcement-learning", "deep-learning", "deep-reinforcement-learning", "machine-learning", "policy-gradient", "deep-q-network", "dqn", "actor-critic", "a3c"], "urls": [], "use_cases": ["learn reinforcement learning from readable code examples", "understand how DQN works with a minimal implementation", "study PPO and actor-critic algorithms in one file", "find reference implementations of Q-learning and SARSA", "compare RL algorithm benchmarks on Atari and CartPole", "get started with deep reinforcement learning in Python"], "what_it_is": "A collection of minimal, clean, one-file-per-algorithm reinforcement learning examples in Python, covering classic methods like Q-Learning and SARSA up to deep RL like DQN, PPO, and A3C. It includes benchmark results on Grid World, CartPole, and Atari environments with reproducible training reports.", "when_to_avoid": ["you need a production-ready RL library with parallel environments and hyperparameter tuning", "you want a framework API to plug algorithms into your own project rather than standalone examples", "you need state-of-the-art performance or extensive multi-seed evaluation"], "when_to_choose": ["you want clean, minimal, educational RL implementations rather than a heavy framework", "you are learning RL algorithms and prefer one readable file per algorithm", "you want reproducible benchmark baselines for DQN and PPO on standard environments"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/rlcode-reinforcement-learning", "repo": "rlcode/reinforcement-learning", "role": "main", "score": 71}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.257080+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:31:36.458528+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "28639711d016cf81266482d6bc971b8bd56d55b9ecfd92cc3c098b3b413b44d9", "fetched_at": "2026-08-28T04:08:13.257080+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rlcode/reinforcement-learning"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.257080+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:31:36.458528+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "28639711d016cf81266482d6bc971b8bd56d55b9ecfd92cc3c098b3b413b44d9", "fetched_at": "2026-08-28T04:08:13.257080+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rlcode/reinforcement-learning"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:31:36.458528+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "28639711d016cf81266482d6bc971b8bd56d55b9ecfd92cc3c098b3b413b44d9", "fetched_at": "2026-08-28T04:08:13.257080+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rlcode/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": "2026-08-28T04:08:13.257080+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.257080+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.257080+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:31:36.458528+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "28639711d016cf81266482d6bc971b8bd56d55b9ecfd92cc3c098b3b413b44d9", "fetched_at": "2026-08-28T04:08:13.257080+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rlcode/reinforcement-learning"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.257080+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.257080+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:31:36.458528+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "28639711d016cf81266482d6bc971b8bd56d55b9ecfd92cc3c098b3b413b44d9", "fetched_at": "2026-08-28T04:08:13.257080+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rlcode/reinforcement-learning"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.257080+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.257080+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.257080+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:31:36.458528+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "28639711d016cf81266482d6bc971b8bd56d55b9ecfd92cc3c098b3b413b44d9", "fetched_at": "2026-08-28T04:08:13.257080+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rlcode/reinforcement-learning"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.257080+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.257080+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:31:36.458528+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "28639711d016cf81266482d6bc971b8bd56d55b9ecfd92cc3c098b3b413b44d9", "fetched_at": "2026-08-28T04:08:13.257080+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rlcode/reinforcement-learning"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:31:36.458528+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "28639711d016cf81266482d6bc971b8bd56d55b9ecfd92cc3c098b3b413b44d9", "fetched_at": "2026-08-28T04:08:13.257080+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rlcode/reinforcement-learning"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:31:36.458528+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "28639711d016cf81266482d6bc971b8bd56d55b9ecfd92cc3c098b3b413b44d9", "fetched_at": "2026-08-28T04:08:13.257080+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rlcode/reinforcement-learning"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:31:36.458528+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "28639711d016cf81266482d6bc971b8bd56d55b9ecfd92cc3c098b3b413b44d9", "fetched_at": "2026-08-28T04:08:13.257080+00:00", "kind": "readme", "missing": false, "url": "https://github.com/rlcode/reinforcement-learning"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 87, "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": 3519, "days_push": 82, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 71, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}