{"adoption": {"forks": 697, "observed_at": "2026-08-28T04:08:05.207084+00:00", "stars": 3448}, "canonical_url": "https://ross.abutalabs.com/products/deeprl", "card": {"archived": false, "artifact_type": "library", "description": "Modularized Implementation of Deep RL Algorithms in PyTorch", "domain": ["reinforcement-learning", "machine-learning", "deep-learning"], "enriched": true, "function": ["machine-learning", "reinforcement-learning", "deep-learning"], "health_score": 20, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["ShangtongZhang/DeepRL"], "name": "ShangtongZhang/DeepRL", "platform": ["python"], "pushed_at": "2024-04-16T19:43:16+00:00", "repo": "ShangtongZhang/DeepRL", "stars": 3448, "tags": ["pytorch", "dqn", "ppo", "ddpg", "td3", "a2c", "option-critic", "atari", "mujoco", "research-code", "gpu", "docker"], "topics": ["pytorch", "deep-reinforcement-learning", "dqn", "dueling-network-architecture", "double-dqn", "deeprl", "ddpg", "ppo", "categorical-dqn", "option-critic", "quantile-regression", "td3", "a2c", "option-critic-architecture", "prioritized-experience-replay", "rainbow"], "urls": [], "use_cases": ["implement deep reinforcement learning algorithms in pytorch", "train a DQN agent on Atari games", "run PPO on Mujoco continuous control tasks", "study reference implementations of Rainbow-style DQN variants", "benchmark deep RL algorithms on a single GPU"], "what_it_is": "A modularized PyTorch implementation of popular deep reinforcement learning algorithms including DQN variants, PPO, DDPG, TD3, A2C, and Option-Critic. It supports switching between toy tasks and Atari/Mujoco benchmark environments.", "when_to_avoid": ["you need a production RL training platform with distributed scaling", "you want the latest maintained framework with broad environment support", "you need algorithms beyond the implemented set or newer PyTorch versions"], "when_to_choose": ["you want readable, modular PyTorch code for classic deep RL algorithms", "you need a research baseline implementation of DQN, PPO, DDPG, or TD3", "you want to reproduce paper results on Atari or Mujoco"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/deeprl", "repo": "ShangtongZhang/DeepRL", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.207084+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:37:35.724568+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "13d283c95a8161c5086abee978b8f1f20c12a1f5c278e37a9a3bb78ef87dfe35", "fetched_at": "2026-08-28T04:08:05.207084+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ShangtongZhang/DeepRL"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.207084+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:37:35.724568+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "13d283c95a8161c5086abee978b8f1f20c12a1f5c278e37a9a3bb78ef87dfe35", "fetched_at": "2026-08-28T04:08:05.207084+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ShangtongZhang/DeepRL"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:37:35.724568+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "13d283c95a8161c5086abee978b8f1f20c12a1f5c278e37a9a3bb78ef87dfe35", "fetched_at": "2026-08-28T04:08:05.207084+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ShangtongZhang/DeepRL"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.207084+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.207084+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.207084+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:37:35.724568+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "13d283c95a8161c5086abee978b8f1f20c12a1f5c278e37a9a3bb78ef87dfe35", "fetched_at": "2026-08-28T04:08:05.207084+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ShangtongZhang/DeepRL"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.207084+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.207084+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:37:35.724568+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "13d283c95a8161c5086abee978b8f1f20c12a1f5c278e37a9a3bb78ef87dfe35", "fetched_at": "2026-08-28T04:08:05.207084+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ShangtongZhang/DeepRL"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.207084+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.207084+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.207084+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:37:35.724568+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "13d283c95a8161c5086abee978b8f1f20c12a1f5c278e37a9a3bb78ef87dfe35", "fetched_at": "2026-08-28T04:08:05.207084+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ShangtongZhang/DeepRL"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.207084+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.207084+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:37:35.724568+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "13d283c95a8161c5086abee978b8f1f20c12a1f5c278e37a9a3bb78ef87dfe35", "fetched_at": "2026-08-28T04:08:05.207084+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ShangtongZhang/DeepRL"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:37:35.724568+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "13d283c95a8161c5086abee978b8f1f20c12a1f5c278e37a9a3bb78ef87dfe35", "fetched_at": "2026-08-28T04:08:05.207084+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ShangtongZhang/DeepRL"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:37:35.724568+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "13d283c95a8161c5086abee978b8f1f20c12a1f5c278e37a9a3bb78ef87dfe35", "fetched_at": "2026-08-28T04:08:05.207084+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ShangtongZhang/DeepRL"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:37:35.724568+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "13d283c95a8161c5086abee978b8f1f20c12a1f5c278e37a9a3bb78ef87dfe35", "fetched_at": "2026-08-28T04:08:05.207084+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ShangtongZhang/DeepRL"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3422, "days_push": 869, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}