{"adoption": {"forks": 192, "observed_at": "2026-08-28T04:04:14.873811+00:00", "stars": 1286}, "canonical_url": "https://ross.abutalabs.com/products/pytorch-rl", "card": {"archived": false, "artifact_type": "library", "description": "PyTorch implementation of Deep Reinforcement Learning: Policy Gradient methods (TRPO, PPO, A2C) and Generative Adversarial Imitation Learning (GAIL). Fast Fisher vector product TRPO.", "domain": ["reinforcement-learning", "machine-learning", "deep-learning", "robotics"], "enriched": true, "function": ["reinforcement-learning", "machine-learning", "deep-learning"], "health_score": 20, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["Khrylx/PyTorch-RL"], "name": "Khrylx/PyTorch-RL", "platform": ["python"], "pushed_at": "2021-02-09T16:17:59+00:00", "repo": "Khrylx/PyTorch-RL", "stars": 1286, "tags": ["pytorch", "policy-gradient", "trpo", "ppo", "a2c", "gail", "imitation-learning", "gym", "mujoco", "fisher-vector-product", "linux", "macos", "gpu"], "topics": ["reinforcement-learning", "policy-gradient", "pytorch-rl", "proximal-policy-optimization", "trpo", "ppo", "pytorch", "a2c", "generative-adversarial-network", "fisher-vectors", "deep-reinforcement-learning"], "urls": [], "use_cases": ["train a PPO agent on a gym environment", "run TRPO with fast Fisher vector products", "implement A2C for discrete and continuous action spaces", "do imitation learning from expert trajectories with GAIL", "collect RL samples in parallel with multiprocessing", "learn policy gradient algorithms from readable code"], "what_it_is": "A PyTorch library implementing deep reinforcement learning policy gradient algorithms (TRPO, PPO, A2C) and Generative Adversarial Imitation Learning (GAIL). It features fast Fisher vector product computation for TRPO and multiprocessing support for parallel sample collection.", "when_to_avoid": ["you need a maintained library with recent PyTorch version support", "you want off-the-shelf support for modern RL algorithms like SAC or DQN", "you need production-grade distributed RL training at scale"], "when_to_choose": ["you want clean, readable PyTorch implementations of TRPO, PPO, A2C, or GAIL", "you need efficient Fisher vector product computation for TRPO", "you are doing research or learning with OpenAI Gym / MuJoCo environments"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/pytorch-rl", "repo": "Khrylx/PyTorch-RL", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:14.873811+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:56:07.500530+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4df9667a08a979b02915b75bc71580766ac9910cf69843121ed8d340ff7e031a", "fetched_at": "2026-08-28T04:04:14.873811+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Khrylx/PyTorch-RL"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:14.873811+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:56:07.500530+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4df9667a08a979b02915b75bc71580766ac9910cf69843121ed8d340ff7e031a", "fetched_at": "2026-08-28T04:04:14.873811+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Khrylx/PyTorch-RL"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:56:07.500530+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4df9667a08a979b02915b75bc71580766ac9910cf69843121ed8d340ff7e031a", "fetched_at": "2026-08-28T04:04:14.873811+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Khrylx/PyTorch-RL"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:14.873811+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:14.873811+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:14.873811+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:56:07.500530+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4df9667a08a979b02915b75bc71580766ac9910cf69843121ed8d340ff7e031a", "fetched_at": "2026-08-28T04:04:14.873811+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Khrylx/PyTorch-RL"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:14.873811+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:14.873811+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:56:07.500530+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4df9667a08a979b02915b75bc71580766ac9910cf69843121ed8d340ff7e031a", "fetched_at": "2026-08-28T04:04:14.873811+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Khrylx/PyTorch-RL"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:14.873811+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:14.873811+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:14.873811+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:56:07.500530+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4df9667a08a979b02915b75bc71580766ac9910cf69843121ed8d340ff7e031a", "fetched_at": "2026-08-28T04:04:14.873811+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Khrylx/PyTorch-RL"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:14.873811+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:14.873811+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:56:07.500530+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4df9667a08a979b02915b75bc71580766ac9910cf69843121ed8d340ff7e031a", "fetched_at": "2026-08-28T04:04:14.873811+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Khrylx/PyTorch-RL"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:56:07.500530+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4df9667a08a979b02915b75bc71580766ac9910cf69843121ed8d340ff7e031a", "fetched_at": "2026-08-28T04:04:14.873811+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Khrylx/PyTorch-RL"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:56:07.500530+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4df9667a08a979b02915b75bc71580766ac9910cf69843121ed8d340ff7e031a", "fetched_at": "2026-08-28T04:04:14.873811+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Khrylx/PyTorch-RL"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:56:07.500530+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4df9667a08a979b02915b75bc71580766ac9910cf69843121ed8d340ff7e031a", "fetched_at": "2026-08-28T04:04:14.873811+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Khrylx/PyTorch-RL"}], "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": 3242, "days_push": 2031, "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}}