{"adoption": {"forks": 231, "observed_at": "2026-08-28T04:03:17.875707+00:00", "stars": 1031}, "canonical_url": "https://ross.abutalabs.com/products/deep-reinforcement-learning-algorithms", "card": {"archived": false, "artifact_type": "learning-resource", "description": "32 projects in the framework of Deep Reinforcement Learning algorithms: Q-learning, DQN, PPO, DDPG, TD3, SAC, A2C and others. Each project is provided with a detailed training log.", "domain": ["reinforcement-learning", "machine-learning", "tutorials", "education"], "enriched": true, "function": ["reinforcement-learning", "machine-learning", "data-science"], "health_score": 20, "homepage": null, "language": "Jupyter Notebook", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["Rafael1s/Deep-Reinforcement-Learning-Algorithms"], "name": "Rafael1s/Deep-Reinforcement-Learning-Algorithms", "platform": ["python", "jvm"], "pushed_at": "2021-06-17T21:58:26+00:00", "repo": "Rafael1s/Deep-Reinforcement-Learning-Algorithms", "stars": 1031, "tags": ["deep-reinforcement-learning", "jupyter-notebooks", "dqn", "ppo", "ddpg", "td3", "sac", "a2c", "q-learning", "udacity", "training-logs", "pybullet", "cartpole", "lunarlander"], "topics": ["deep-rl-algorithms", "github-udacity", "dqn-ppo-ddpg", "dqn", "td3", "cartpole", "bipedalwalker", "deep-reinforcement-learning", "sac", "carracing", "hopperbulletenv", "lunarlander", "ddpg", "ppo", "a2c", "antbulletenv", "soft-actor-critic", "halfcheetahbulletenv", "walker2dbulletenv"], "urls": [], "use_cases": ["learn deep reinforcement learning algorithms with worked examples", "see training logs for DQN on CartPole or LunarLander", "compare PPO vs DDPG vs TD3 vs SAC implementations", "study policy-gradient and actor-critic methods in notebooks", "find reference implementations for Udacity DRL nanodegree projects", "understand how to solve continuous control environments like BipedalWalker"], "what_it_is": "A collection of 32 Jupyter Notebook projects implementing deep reinforcement learning algorithms such as Q-learning, DQN, PPO, DDPG, TD3, SAC, and A2C across many environments like CartPole, LunarLander, and BipedalWalker. Each project includes a detailed training log, making it a reference and educational resource for studying RL methods.", "when_to_avoid": ["you need a production-ready or maintained RL library with an API", "you want a single unified framework rather than 32 separate notebooks", "you need actively updated code or official license terms"], "when_to_choose": ["you want readable notebook-style implementations of classic deep RL algorithms", "you are studying RL and want to see full training logs and results", "you need reference code for Udacity DRL nanodegree environments"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/deep-reinforcement-learning-algorithms", "repo": "Rafael1s/Deep-Reinforcement-Learning-Algorithms", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.875707+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:07:25.101281+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e67187f91c75be3786aea783f39e6ba9481bc77efe313d7345ccf5d12b7f0e5c", "fetched_at": "2026-08-28T04:03:17.875707+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Rafael1s/Deep-Reinforcement-Learning-Algorithms"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.875707+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:07:25.101281+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e67187f91c75be3786aea783f39e6ba9481bc77efe313d7345ccf5d12b7f0e5c", "fetched_at": "2026-08-28T04:03:17.875707+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Rafael1s/Deep-Reinforcement-Learning-Algorithms"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:07:25.101281+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e67187f91c75be3786aea783f39e6ba9481bc77efe313d7345ccf5d12b7f0e5c", "fetched_at": "2026-08-28T04:03:17.875707+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Rafael1s/Deep-Reinforcement-Learning-Algorithms"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.875707+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.875707+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.875707+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:07:25.101281+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e67187f91c75be3786aea783f39e6ba9481bc77efe313d7345ccf5d12b7f0e5c", "fetched_at": "2026-08-28T04:03:17.875707+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Rafael1s/Deep-Reinforcement-Learning-Algorithms"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.875707+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.875707+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:07:25.101281+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e67187f91c75be3786aea783f39e6ba9481bc77efe313d7345ccf5d12b7f0e5c", "fetched_at": "2026-08-28T04:03:17.875707+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Rafael1s/Deep-Reinforcement-Learning-Algorithms"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.875707+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.875707+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.875707+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:07:25.101281+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e67187f91c75be3786aea783f39e6ba9481bc77efe313d7345ccf5d12b7f0e5c", "fetched_at": "2026-08-28T04:03:17.875707+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Rafael1s/Deep-Reinforcement-Learning-Algorithms"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.875707+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.875707+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:07:25.101281+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e67187f91c75be3786aea783f39e6ba9481bc77efe313d7345ccf5d12b7f0e5c", "fetched_at": "2026-08-28T04:03:17.875707+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Rafael1s/Deep-Reinforcement-Learning-Algorithms"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:07:25.101281+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e67187f91c75be3786aea783f39e6ba9481bc77efe313d7345ccf5d12b7f0e5c", "fetched_at": "2026-08-28T04:03:17.875707+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Rafael1s/Deep-Reinforcement-Learning-Algorithms"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:07:25.101281+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e67187f91c75be3786aea783f39e6ba9481bc77efe313d7345ccf5d12b7f0e5c", "fetched_at": "2026-08-28T04:03:17.875707+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Rafael1s/Deep-Reinforcement-Learning-Algorithms"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:07:25.101281+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e67187f91c75be3786aea783f39e6ba9481bc77efe313d7345ccf5d12b7f0e5c", "fetched_at": "2026-08-28T04:03:17.875707+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Rafael1s/Deep-Reinforcement-Learning-Algorithms"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2705, "days_push": 1903, "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}}