{"adoption": {"forks": 385, "observed_at": "2026-08-28T04:06:11.871456+00:00", "stars": 2085}, "canonical_url": "https://ross.abutalabs.com/products/on-policy", "card": {"archived": false, "artifact_type": "library", "description": "This is the official implementation of Multi-Agent PPO (MAPPO).", "domain": ["reinforcement-learning", "machine-learning", "artificial-intelligence", "gaming-tools"], "enriched": true, "function": ["reinforcement-learning", "machine-learning", "benchmarking"], "health_score": 20, "homepage": "https://sites.google.com/view/mappo", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["marlbenchmark/on-policy"], "name": "marlbenchmark/on-policy", "platform": ["python"], "pushed_at": "2024-07-18T10:00:36+00:00", "repo": "marlbenchmark/on-policy", "stars": 2085, "tags": ["mappo", "ppo", "multi-agent", "marl", "smac", "hanabi", "starcraft2", "google-football", "pytorch", "research-code", "gpu", "linux"], "topics": ["hanabi", "mappo", "smac", "mpes", "starcraftii", "ppo", "multi-agent", "algorithms"], "urls": [], "use_cases": ["train multi-agent reinforcement learning policies with PPO", "reproduce MAPPO benchmark results on SMAC or Hanabi", "compare on-policy vs off-policy algorithms in cooperative multi-agent games", "get a strong baseline for multi-agent RL research", "run RL experiments on StarCraftII SMAC v2 or Google Research Football", "study ablation factors that affect PPO performance in multi-agent settings"], "what_it_is": "The official PyTorch implementation of Multi-Agent PPO (MAPPO), an on-policy reinforcement learning algorithm for cooperative multi-agent settings. It includes environment wrappers, training runners, and tuned hyperparameter scripts for benchmarks such as SMAC, SMACv2, Hanabi, MPEs, and Google Research Football.", "when_to_avoid": ["you need off-policy multi-agent algorithms like QMIX or MADDPG", "you want a general-purpose RL library with many algorithms rather than a focused MAPPO implementation", "you lack a GPU or the specific environment dependencies (StarCraftII, Hanabi, etc.)"], "when_to_choose": ["you need a well-tuned, paper-backed MAPPO baseline for cooperative multi-agent benchmarks", "you want reproducible training scripts with published hyperparameters and curves", "your research targets SMAC, Hanabi, MPEs, or Google Research Football environments"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/on-policy", "repo": "marlbenchmark/on-policy", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.871456+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:55:50.459923+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "031d006c12c29a1e65fc05dfa6a2ef06dc466b8d92e732de43ccbba282d58b65", "fetched_at": "2026-08-28T04:06:11.871456+00:00", "kind": "readme", "missing": false, "url": "https://github.com/marlbenchmark/on-policy"}, {"content_hash": "39ffe723e5ade3d3e16d7b5e69a654c4c13af05a5fe462dc078bf5443a4ef83d", "fetched_at": "2026-08-29T10:35:47.604358+00:00", "kind": "homepage", "missing": false, "url": "https://sites.google.com/view/mappo"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.871456+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:55:50.459923+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "031d006c12c29a1e65fc05dfa6a2ef06dc466b8d92e732de43ccbba282d58b65", "fetched_at": "2026-08-28T04:06:11.871456+00:00", "kind": "readme", "missing": false, "url": "https://github.com/marlbenchmark/on-policy"}, {"content_hash": "39ffe723e5ade3d3e16d7b5e69a654c4c13af05a5fe462dc078bf5443a4ef83d", "fetched_at": "2026-08-29T10:35:47.604358+00:00", "kind": "homepage", "missing": false, "url": "https://sites.google.com/view/mappo"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:55:50.459923+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "031d006c12c29a1e65fc05dfa6a2ef06dc466b8d92e732de43ccbba282d58b65", "fetched_at": "2026-08-28T04:06:11.871456+00:00", "kind": "readme", "missing": false, "url": "https://github.com/marlbenchmark/on-policy"}, {"content_hash": "39ffe723e5ade3d3e16d7b5e69a654c4c13af05a5fe462dc078bf5443a4ef83d", "fetched_at": "2026-08-29T10:35:47.604358+00:00", "kind": "homepage", "missing": false, "url": "https://sites.google.com/view/mappo"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.871456+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.871456+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.871456+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:55:50.459923+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "031d006c12c29a1e65fc05dfa6a2ef06dc466b8d92e732de43ccbba282d58b65", "fetched_at": "2026-08-28T04:06:11.871456+00:00", "kind": "readme", "missing": false, "url": "https://github.com/marlbenchmark/on-policy"}, {"content_hash": "39ffe723e5ade3d3e16d7b5e69a654c4c13af05a5fe462dc078bf5443a4ef83d", "fetched_at": "2026-08-29T10:35:47.604358+00:00", "kind": "homepage", "missing": false, "url": "https://sites.google.com/view/mappo"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.871456+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.871456+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:55:50.459923+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "031d006c12c29a1e65fc05dfa6a2ef06dc466b8d92e732de43ccbba282d58b65", "fetched_at": "2026-08-28T04:06:11.871456+00:00", "kind": "readme", "missing": false, "url": "https://github.com/marlbenchmark/on-policy"}, {"content_hash": "39ffe723e5ade3d3e16d7b5e69a654c4c13af05a5fe462dc078bf5443a4ef83d", "fetched_at": "2026-08-29T10:35:47.604358+00:00", "kind": "homepage", "missing": false, "url": "https://sites.google.com/view/mappo"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.871456+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.871456+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.871456+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:55:50.459923+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "031d006c12c29a1e65fc05dfa6a2ef06dc466b8d92e732de43ccbba282d58b65", "fetched_at": "2026-08-28T04:06:11.871456+00:00", "kind": "readme", "missing": false, "url": "https://github.com/marlbenchmark/on-policy"}, {"content_hash": "39ffe723e5ade3d3e16d7b5e69a654c4c13af05a5fe462dc078bf5443a4ef83d", "fetched_at": "2026-08-29T10:35:47.604358+00:00", "kind": "homepage", "missing": false, "url": "https://sites.google.com/view/mappo"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.871456+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.871456+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:55:50.459923+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "031d006c12c29a1e65fc05dfa6a2ef06dc466b8d92e732de43ccbba282d58b65", "fetched_at": "2026-08-28T04:06:11.871456+00:00", "kind": "readme", "missing": false, "url": "https://github.com/marlbenchmark/on-policy"}, {"content_hash": "39ffe723e5ade3d3e16d7b5e69a654c4c13af05a5fe462dc078bf5443a4ef83d", "fetched_at": "2026-08-29T10:35:47.604358+00:00", "kind": "homepage", "missing": false, "url": "https://sites.google.com/view/mappo"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:55:50.459923+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "031d006c12c29a1e65fc05dfa6a2ef06dc466b8d92e732de43ccbba282d58b65", "fetched_at": "2026-08-28T04:06:11.871456+00:00", "kind": "readme", "missing": false, "url": "https://github.com/marlbenchmark/on-policy"}, {"content_hash": "39ffe723e5ade3d3e16d7b5e69a654c4c13af05a5fe462dc078bf5443a4ef83d", "fetched_at": "2026-08-29T10:35:47.604358+00:00", "kind": "homepage", "missing": false, "url": "https://sites.google.com/view/mappo"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:55:50.459923+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "031d006c12c29a1e65fc05dfa6a2ef06dc466b8d92e732de43ccbba282d58b65", "fetched_at": "2026-08-28T04:06:11.871456+00:00", "kind": "readme", "missing": false, "url": "https://github.com/marlbenchmark/on-policy"}, {"content_hash": "39ffe723e5ade3d3e16d7b5e69a654c4c13af05a5fe462dc078bf5443a4ef83d", "fetched_at": "2026-08-29T10:35:47.604358+00:00", "kind": "homepage", "missing": false, "url": "https://sites.google.com/view/mappo"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:55:50.459923+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "031d006c12c29a1e65fc05dfa6a2ef06dc466b8d92e732de43ccbba282d58b65", "fetched_at": "2026-08-28T04:06:11.871456+00:00", "kind": "readme", "missing": false, "url": "https://github.com/marlbenchmark/on-policy"}, {"content_hash": "39ffe723e5ade3d3e16d7b5e69a654c4c13af05a5fe462dc078bf5443a4ef83d", "fetched_at": "2026-08-29T10:35:47.604358+00:00", "kind": "homepage", "missing": false, "url": "https://sites.google.com/view/mappo"}], "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": 2017, "days_push": 776, "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}}