{"adoption": {"forks": 895, "observed_at": "2026-08-28T04:08:55.628839+00:00", "stars": 4651}, "canonical_url": "https://ross.abutalabs.com/products/deep-reinforcement-learning-with-pytorch", "card": {"archived": false, "artifact_type": "learning-resource", "description": "PyTorch implementation of DQN, AC,  ACER, A2C, A3C, PG,  DDPG, TRPO, PPO, SAC, TD3 and ....", "domain": ["reinforcement-learning", "machine-learning", "deep-learning", "tutorials"], "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": ["sweetice/Deep-reinforcement-learning-with-pytorch"], "name": "sweetice/Deep-reinforcement-learning-with-pytorch", "platform": ["python", "cross-platform"], "pushed_at": "2023-03-24T23:36:09+00:00", "repo": "sweetice/Deep-reinforcement-learning-with-pytorch", "stars": 4651, "tags": ["pytorch", "dqn", "ppo", "actor-critic", "sac", "td3", "a3c", "ddpg", "trpo", "policy-gradient", "educational"], "topics": ["policy-gradient", "pytorch", "actor-critic-algorithm", "alphago", "deep-reinforcement-learning", "a2c", "dqn", "sarsa", "ppo", "a3c", "resnet", "algorithm", "deep-learning", "reinforce", "actor-critic", "sac", "td3", "trpo"], "urls": [], "use_cases": ["learn deep reinforcement learning algorithms with pytorch", "study dqn implementation on cartpole", "understand ppo and sac algorithm code", "reference implementations of actor-critic methods", "compare policy gradient algorithms side by side", "run td3 on bipedalwalker"], "what_it_is": "A collection of clear PyTorch implementations of classic and state-of-the-art deep reinforcement learning algorithms such as DQN, A3C, PPO, SAC, TD3, and TRPO. It is designed as an educational resource for people learning deep RL algorithms.", "when_to_avoid": ["you need a production-ready or well-maintained RL framework", "you require modern Python versions or up-to-date dependencies", "you need a stable API for training RL agents at scale"], "when_to_choose": ["you want readable educational implementations of RL algorithms", "you are learning deep RL and want to read clean pytorch code", "you need reference code for DQN, PPO, SAC, TD3, or related algorithms"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/deep-reinforcement-learning-with-pytorch", "repo": "sweetice/Deep-reinforcement-learning-with-pytorch", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.628839+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:19:30.095603+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "84317356f54a800fdfa12896938f721600f39796857f542d5d00b0962201b0dc", "fetched_at": "2026-08-28T04:08:55.628839+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sweetice/Deep-reinforcement-learning-with-pytorch"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.628839+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:19:30.095603+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "84317356f54a800fdfa12896938f721600f39796857f542d5d00b0962201b0dc", "fetched_at": "2026-08-28T04:08:55.628839+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sweetice/Deep-reinforcement-learning-with-pytorch"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:19:30.095603+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "84317356f54a800fdfa12896938f721600f39796857f542d5d00b0962201b0dc", "fetched_at": "2026-08-28T04:08:55.628839+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sweetice/Deep-reinforcement-learning-with-pytorch"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.628839+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.628839+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.628839+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:19:30.095603+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "84317356f54a800fdfa12896938f721600f39796857f542d5d00b0962201b0dc", "fetched_at": "2026-08-28T04:08:55.628839+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sweetice/Deep-reinforcement-learning-with-pytorch"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.628839+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.628839+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:19:30.095603+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "84317356f54a800fdfa12896938f721600f39796857f542d5d00b0962201b0dc", "fetched_at": "2026-08-28T04:08:55.628839+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sweetice/Deep-reinforcement-learning-with-pytorch"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.628839+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.628839+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.628839+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:19:30.095603+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "84317356f54a800fdfa12896938f721600f39796857f542d5d00b0962201b0dc", "fetched_at": "2026-08-28T04:08:55.628839+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sweetice/Deep-reinforcement-learning-with-pytorch"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.628839+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:55.628839+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:19:30.095603+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "84317356f54a800fdfa12896938f721600f39796857f542d5d00b0962201b0dc", "fetched_at": "2026-08-28T04:08:55.628839+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sweetice/Deep-reinforcement-learning-with-pytorch"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:19:30.095603+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "84317356f54a800fdfa12896938f721600f39796857f542d5d00b0962201b0dc", "fetched_at": "2026-08-28T04:08:55.628839+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sweetice/Deep-reinforcement-learning-with-pytorch"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:19:30.095603+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "84317356f54a800fdfa12896938f721600f39796857f542d5d00b0962201b0dc", "fetched_at": "2026-08-28T04:08:55.628839+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sweetice/Deep-reinforcement-learning-with-pytorch"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:19:30.095603+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "84317356f54a800fdfa12896938f721600f39796857f542d5d00b0962201b0dc", "fetched_at": "2026-08-28T04:08:55.628839+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sweetice/Deep-reinforcement-learning-with-pytorch"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "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": 3008, "days_push": 1258, "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}}