{"adoption": {"forks": 147, "observed_at": "2026-08-28T04:04:29.689196+00:00", "stars": 1358}, "canonical_url": "https://ross.abutalabs.com/products/popular-rl-algorithms", "card": {"archived": false, "artifact_type": "learning-resource", "description": "PyTorch implementation of Soft Actor-Critic (SAC), Twin Delayed DDPG (TD3), Actor-Critic (AC/A2C), Proximal Policy Optimization (PPO), QT-Opt, PointNet..", "domain": ["reinforcement-learning", "machine-learning", "tutorials"], "enriched": true, "function": ["machine-learning", "reinforcement-learning"], "health_score": 27, "homepage": null, "language": "Jupyter Notebook", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["quantumiracle/Popular-RL-Algorithms"], "name": "quantumiracle/Popular-RL-Algorithms", "platform": ["python"], "pushed_at": "2025-03-13T20:22:24+00:00", "repo": "quantumiracle/Popular-RL-Algorithms", "stars": 1358, "tags": ["pytorch", "model-free-rl", "openai-gym", "sac", "td3", "ppo", "research-code", "jupyter-notebook"], "topics": ["reinforcement-learning", "soft-actor-critic", "state-of-the-art"], "urls": [], "use_cases": ["learn how SAC is implemented in PyTorch", "compare multiple implementations of the same RL algorithm", "study PPO or TD3 source code for a course", "find reference code for model-free RL algorithms", "get a starting point for implementing a custom RL algorithm", "understand differences between SAC versions"], "what_it_is": "A personal collection of PyTorch implementations of popular model-free reinforcement learning algorithms (SAC, TD3, PPO, DDPG, Q-learning, QMIX, and more) tested on OpenAI Gym and a custom Reacher environment. It is a study/research reference rather than a packaged library, with multiple implementation variants shown for comparison.", "when_to_avoid": ["you need a production-ready or well-structured RL library", "you want a stable high-level API for training RL agents", "you need maintained, tested code with clean abstractions"], "when_to_choose": ["you want readable, educational implementations of classic RL algorithms", "you want to see multiple variants of an algorithm side by side", "you are studying reinforcement learning and want reference code rather than a black-box library"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/popular-rl-algorithms", "repo": "quantumiracle/Popular-RL-Algorithms", "role": "main", "score": 37}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:29.689196+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:41:46.898266+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "74da5197795f106cb07d8b9b785e7f5c3fa86fd61863d286704ec744709e2668", "fetched_at": "2026-08-28T04:04:29.689196+00:00", "kind": "readme", "missing": false, "url": "https://github.com/quantumiracle/Popular-RL-Algorithms"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:29.689196+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:41:46.898266+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "74da5197795f106cb07d8b9b785e7f5c3fa86fd61863d286704ec744709e2668", "fetched_at": "2026-08-28T04:04:29.689196+00:00", "kind": "readme", "missing": false, "url": "https://github.com/quantumiracle/Popular-RL-Algorithms"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:41:46.898266+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "74da5197795f106cb07d8b9b785e7f5c3fa86fd61863d286704ec744709e2668", "fetched_at": "2026-08-28T04:04:29.689196+00:00", "kind": "readme", "missing": false, "url": "https://github.com/quantumiracle/Popular-RL-Algorithms"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:29.689196+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:29.689196+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:29.689196+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:41:46.898266+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "74da5197795f106cb07d8b9b785e7f5c3fa86fd61863d286704ec744709e2668", "fetched_at": "2026-08-28T04:04:29.689196+00:00", "kind": "readme", "missing": false, "url": "https://github.com/quantumiracle/Popular-RL-Algorithms"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:29.689196+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:29.689196+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:41:46.898266+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "74da5197795f106cb07d8b9b785e7f5c3fa86fd61863d286704ec744709e2668", "fetched_at": "2026-08-28T04:04:29.689196+00:00", "kind": "readme", "missing": false, "url": "https://github.com/quantumiracle/Popular-RL-Algorithms"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:29.689196+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:29.689196+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:29.689196+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:41:46.898266+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "74da5197795f106cb07d8b9b785e7f5c3fa86fd61863d286704ec744709e2668", "fetched_at": "2026-08-28T04:04:29.689196+00:00", "kind": "readme", "missing": false, "url": "https://github.com/quantumiracle/Popular-RL-Algorithms"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:29.689196+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:29.689196+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:41:46.898266+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "74da5197795f106cb07d8b9b785e7f5c3fa86fd61863d286704ec744709e2668", "fetched_at": "2026-08-28T04:04:29.689196+00:00", "kind": "readme", "missing": false, "url": "https://github.com/quantumiracle/Popular-RL-Algorithms"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:41:46.898266+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "74da5197795f106cb07d8b9b785e7f5c3fa86fd61863d286704ec744709e2668", "fetched_at": "2026-08-28T04:04:29.689196+00:00", "kind": "readme", "missing": false, "url": "https://github.com/quantumiracle/Popular-RL-Algorithms"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:41:46.898266+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "74da5197795f106cb07d8b9b785e7f5c3fa86fd61863d286704ec744709e2668", "fetched_at": "2026-08-28T04:04:29.689196+00:00", "kind": "readme", "missing": false, "url": "https://github.com/quantumiracle/Popular-RL-Algorithms"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:41:46.898266+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "74da5197795f106cb07d8b9b785e7f5c3fa86fd61863d286704ec744709e2668", "fetched_at": "2026-08-28T04:04:29.689196+00:00", "kind": "readme", "missing": false, "url": "https://github.com/quantumiracle/Popular-RL-Algorithms"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 11, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2693, "days_push": 538, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 37, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}